Recent-Stars-2025

KO | EN

gitlite — search

#nlp #linux #animation #cli #ai #http #devops #self-hosted #dotnet #ruby

Recent-Stars-2025

(★ 1,048)

🔥SLAM, VIsual localization, keypoint detection, Image matching, Pose/Object tracking, Depth/Disparity/Flow Estimation, 3D-graphic, etc. related papers and code

Recent-Stars-2025 Latest Version Download

ZIP Download

# Use via CDN

jsDelivr

jsDelivr serves any public GitHub repository as a CDN with zero setup. Pick a version and a file to get a ready-to-paste link and snippet.

Version

File path

Link

Example

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

<p align="center">
 <img width="100px" src="github-star.svg" align="center" alt="Recent-Stars-2020" />
 <h1 align="center">Recent Stars 2025</h1>
 <p align="center">✔ This repo collects some links with papers which I recently starred related on SLAM, Pose/Object tracking, Depth/Disparity/Flow Estimation, 3D-graphic, etc.</p>
</p>

## Update: This repository is no longer actively maintained.

近期写了一个自动获取Arxiv上有关SLAM/特征提取匹配/视觉定位等领域论文的小工具[**cv-arxiv-daily**](https://github.com/Vincentqyw/cv-arxiv-daily)，每日更新，欢迎大家关注。
Recommend: A useful [tool](https://github.com/Vincentqyw/cv-arxiv-daily) to automatically update CV papers daily using github actions (Update Every day)

## SLAM related

最近主要关注视觉定位+SFM算法（Last Update: **2022.03.31**）

- [**Localization**] [CrossLoc: Scalable Aerial Localization Assisted by Multimodal Synthetic Data](https://github.com/TOPO-EPFL/CrossLoc), CVPR 2022, **[[PDF](https://arxiv.org/abs/2112.09081)]**, **[[Video](https://youtu.be/pytRRXPFqFE)]**, **[[Website](https://crossloc.github.io/)]**, **[[Dataset](https://doi.org/10.5061/dryad.mgqnk991c)]**, 为空中无人机视角提供sim2real视觉定位的end-to-end方案，虚拟数据生成工具+大规模高精度数据集+multi-modal视觉定位算法

- [**Light Flow**] [Learning Optical Flow from a Few Matches](https://github.com/zacjiang/SCV), CVPR 2021, **[[PDF](https://arxiv.org/abs/2104.02166)]**, 光流估计

- [**SFM**] [Beyond Controlled Environments: 3D Camera Re-Localization in Changing Indoor Scenes](https://github.com/tsattler/MultiCameraPose), ECCV 2020, **[[PDF](https://arxiv.org/abs/2008.02004)]**, 已知2D-3D关联和相对位姿，用于多相机位姿估计

- [**SLAM**] [Tangent Space Backpropagation for 3D Transformation Groups](https://github.com/princeton-vl/lietorch), CVPR 2021, **[[PDF](https://arxiv.org/abs/2103.12032)]**, 使用Torch实现李群反向传播

- [**Localization**] [Visual-Based-Localization-Papers](https://github.com/Johnzdh/awesome-visual-localization-papers), 视觉定位相关论文集

- [**Localization**] [kapture-localization: toolbox](https://github.com/naver/kapture-localization), 基于[kapture](https://github.com/naver/kapture)的视觉定位流程

- [**Localization**] [SeqNet: Learning Descriptors for Sequence-based Hierarchical Place Recognition](https://github.com/oravus/seqNet), ICRA 2021, **[[PDF](https://arxiv.org/abs/2102.11603)]**,**[[Video](https://www.youtube.com/watch?v=KYw7RhDfxY0)]**, 一种基于图像序列的场景识别算法

- [**Event Camera**] [DSEC: A Stereo Event Camera Dataset for Driving Scenarios](https://github.com/uzh-rpg/DSEC), CVPRW 2021, **[[PDF](http://rpg.ifi.uzh.ch/docs/RAL21_DSEC.pdf)]**,**[[Homepage](https://dsec.ifi.uzh.ch/)]**, 自动驾驶环境下，使用事件相机+双目全局曝光+LIDAR+RTK GPS采集的数据集

- [**SFM**] [openMVS_comments](https://github.com/electech6/openMVS_comments), OpenMVS 注释版

- [**3D Reconstruction**] [J3DReconstruction](https://github.com/SoulBasic/J3DReconstruction), Windows下基于openMVG+openMVS的三维重建解决方案以及基于Qt的可视化桌面平台

- [**PointCloud**] [3D-PointCloud](https://github.com/zhulf0804/3D-PointCloud), 点云相关论文以及数据集

- [**SLAM**] [VIDO-SLAM](https://github.com/bxh1/VIDO-SLAM), 单目相机紧耦合动态物体环境下SLAM

- [**SLAM**] [Interactive Visualisation of Gaussian processes](https://github.com/st--/interactive-gp-visualization), **[[Homepage](http://www.infinitecuriosity.org/vizgp/)]**, 高斯过程动画演示

- [**SFM**] [ROBA: Rotation-Only Bundle Adjustment](https://github.com/sunghoon031/ROBA), CVPR 2021, **[[PDF](https://arxiv.org/abs/2011.11724)]**,**[[Video](https://www.youtube.com/watch?v=JXnEwXwVKus)]**, 高效优化旋转量，用于全局SFM，提高SFM精度

- [**Localization**] [Fusion-DHL: WiFi, IMU, and Floorplan Fusion for Dense History of Locations in Indoor Environments](https://github.com/Sachini/Fusion-DHL), ICRA 2021, **[[PDF](https://arxiv.org/abs/2105.08837)]**,**[[Video](https://youtu.be/CCDms7KWgI8)]**, 多模态（WiFi,IMU,Floorplan）传感器数据融合室内定位

- [**SLAM**] [VINS-GPS-Wheel](https://github.com/Wallong/VINS-GPS-Wheel), 基于VINS-Mono开发的SLAM算法，轮式紧耦合，GPS松耦合

- [**SLAM**] [OpenREALM](https://github.com/laxnpander/OpenREALM),**[[Video](https://www.youtube.com/watch?v=9MvPTHP0r0c)]**, 基于OpenVSLAM开发的一套开源SLAM框架，可用于实时无人机建图定位

- [**Localization**] [InLoc_demo](https://github.com/HajimeTaira/InLoc_demo), 用于验证室内数据集InLoc视觉定位效果的演示脚本

- [**L-SLAM**] [T-LOAM: Truncated Least Squares Lidar-only Odometry and Mapping in Real-Time](https://github.com/zpw6106/tloam), TGRS 2021, **[[PDF](https://ieeexplore.ieee.org/document/9446309)]**,**[[Video](https://www.youtube.com/watch?v=YwINGyaRXVQ)]**, 使用截断最小二乘+Open3D点云库实现SLAM

- [**SLAM**] [ADEKF](https://github.com/TomLKoller/ADEKF), 无需定义雅可比，ceres实现自动微分卡尔曼滤波

- [**L-SLAM**] [Locus: LiDAR-based Place Recognition using Spatiotemporal Higher-Order Pooling](https://github.com/csiro-robotics/locus), ICRA 2021, **[[PDF](https://arxiv.org/abs/2011.14497)]**,**[[Homepage](https://research.csiro.au/robotics/locus-pr)]**, 3D点云全局描述子实现场景识别

- [**Matching**] [COTR: Correspondence Transformer for Matching Across Images](https://github.com/ubc-vision/COTR), CVPR 2021, **[[PDF](https://arxiv.org/abs/2103.14167)]**,**[[Homepage](https://jiangwei221.github.io/vids/cotr/README.html)]**, 基于Transformer的图像匹配，非特征点也可匹配

- [**Matching**] [NRE: Neural Reprojection Error: Merging Feature Learning and Camera Pose Estimation](https://github.com/germain-hug/NRE), CVPR 2021, **[[PDF](https://arxiv.org/abs/2103.07153)]**,**[[Homepage](https://www.hugogermain.com/nre)]**, 改进传统的重投影误差，使用深度学习重新设计重投影误差的形式，实现特征匹配和相机位姿估计

- [**Matching**][Learning Accurate Dense Correspondences and When to Trust Them](https://github.com/PruneTruong/DenseMatching), CVPR 2021 (Oral), **[[PDF](https://arxiv.org/abs/2101.01710)]**,稠密特征匹配

- [**SFM**][How privacy preserving are Line Clouds? Recovering Scene Details from 3D Lines](https://github.com/kunalchelani/Line2Point), CVPR 2021, **[[PDF](https://openaccess.thecvf.com/content/CVPR2021/html/Chelani_How_Privacy-Preserving_Are_Line_Clouds_Recovering_Scene_Details_From_3D_CVPR_2021_paper.html)]**,**[[Video](https://www.youtube.com/watch?v=PdwGHHizKXM)]**,隐私保护SFM将模型中的点转换成了线，视觉（人）根本看不出场景的原本的样子，本文反向将这些线转换成了点 ，进而恢复场景的结构。

- [**L-SLAM**][R2LIVE: A Robust, Real-time, LiDAR-Inertial-Visual tightly-coupled state Estimator and mapping](https://github.com/hku-mars/r2live), arxiv 2020, **[[PDF](https://arxiv.org/abs/2102.12400)]**,**[[Video](https://www.youtube.com/watch?v=9lqRHmlN_MA)]**,激光+IMU+视觉紧耦合SLAM

- [**SFM**] [InvSFM: Revealing Scenes by Inverting Structure from Motion Reconstructions](https://github.com/francescopittaluga/invsfm), CVPR 2019 (Oral), **[[PDF](https://openaccess.thecvf.com/content_CVPR_2019/papers/Pittaluga_Revealing_Scenes_by_Inverting_Structure_From_Motion_Reconstructions_CVPR_2019_paper.pdf)]**,**[[Homepage](https://www.francescopittaluga.com/invsfm/index.html)]**, 反向SFM，从点云恢复场景

- [**Feature**] [LETR: Line Segment Detection Using Transformers without Edges](https://github.com/mlpc-ucsd/LETR), CVPR2021 (Oral), **[[PDF](https://arxiv.org/abs/2101.01909)]**, 利用Transformer实现端到端线段提取

- [**Feature**] [FFD: Fast Feature Detector](https://github.com/mogvision/FFD), TIP 2020, **[[PDF](https://arxiv.org/pdf/2012.00859.pdf)]**, **[[Blog](https://mp.weixin.qq.com/s?__biz=MzI3NDIyMjcyNg==&mid=2652168629&idx=1&sn=e9d845d4371f0eb3f5d3da0cc3c161a5&chksm=f0f71a5cc780934af41f1d08fc9ef752a11198157b96b849da179e5131e9bc66cf62a6bb3c31&token=208229741&lang=zh_CN#rd)]**，传统方式实现快速特征提取器，该方法的复杂度小于目前流行SIFT约5%

- [**Feature**] [Learning and aggregating deep local descriptors for instance-level recognition](https://github.com/gtolias/how), ECCV 2020, **[[PDF](https://arxiv.org/abs/2007.13172)]**, 深度局部描述子实现instance-level的识别

- [**Mapping**] [Multi-View Optimization of Local Feature Geometry](https://github.com/mihaidusmanu/local-feature-refinement), ECCV 2020, **[[PDF](https://arxiv.org/abs/2003.08348)]**,**[[Homepage](https://dsmn.ml/publications/mvolfg.html)]**，多视角优化2D点进而提高SFM建图的精度，如降低平均重投影误差

- [**Localization&Mapping**] [Cross-Descriptor Visual Localization and Mapping](https://github.com/mihaidusmanu/cross-descriptor-vis-loc-map), arxiv 2020, **[[PDF](http://xxx.itp.ac.cn//pdf/2012.01377.pdf)]**, 跨描述子视觉建图与定位：能够使建图特征进行“更新”以及实现了跨特征类型的匹配（如使用SIFT建立的场景模型，可以用HardNet进行定位）

- [**SLAM**] [CamVox: A Low-cost and Accurate Lidar-assisted Visual SLAM System](https://github.com/ISEE-Technology/CamVox), arxiv 2020, **[[PDF](https://arxiv.org/abs/2011.11357)]**，**[[Blog](https://mp.weixin.qq.com/s?__biz=MzI3NDIyMjcyNg==&mid=2652168464&idx=2&sn=339ccc5575fc8a766ddbed1d8026554a&chksm=f0f71af9c78093efc9208bed3792d1ac27e3232fbd5e274c4b9dce21b0172ff3a014386f7fc4&token=208229741&lang=zh_CN#rd)]**，相机和激光雷达融合（SLAM）

- [**Localization**] [Stereo Localization in LiDAR Maps](https://github.com/tony1098/Stereo-Localization-in-LiDAR-Maps), 跨模态定位：在LiDAR地图中使用视觉图像定位

- [**Localization**] Augmenting Visual Place Recognition with Structural Cues, Robotics and Automation Letters (RA-L) 2020, **[[PDF](http://rpg.ifi.uzh.ch/docs/RAL20_Oertel.pdf)]**，**[[Homepage](http://rpg.ifi.uzh.ch/research_vo.html)]**，结合外观以及3D结构线索增强视觉定位，目前效果远超NetVLad

- [**Localization**][CMRNet: Camera to LiDAR-Map Registration](https://github.com/cattaneod/CMRNet), **PDF**: **[[CMRNet, ITSC 2019](https://arxiv.org/abs/1906.10109)]**, **[[CMRNet++, ICRA 2020](https://arxiv.org/abs/2004.13795)]**, **[[Homepage](http://vloc-in-lidar.cs.uni-freiburg.de/)]**，在LIDAR地图中用RGB定位，以初始位姿开始，迭代出定位位姿

- [**Localization**][AtLoc: Attention Guided Camera Localization](https://github.com/BingCS/AtLoc), AAAI 2020, **[[PDF](https://arxiv.org/abs/1909.03557)]**，注意力机制视觉定位

- [**Localization**][Hierarchical-Localization](https://github.com/cvg/Hierarchical-Localization), **PDF**, **[[From Coarse to Fine: Robust Hierarchical Localization at Large Scale,CVPR 2019](https://arxiv.org/abs/1812.03506)]**, **[[SuperGlue: Learning Feature Matching with Graph Neural Networks, CVPR 2020](https://arxiv.org/abs/1911.11763)]**, 目前视觉定位挑战赛[visuallocalization.net/benchmark](https://www.visuallocalization.net/benchmark/) TOP 1的算法（使用了Hierarchical Localization - SuperPoint + SuperGlue）。

- [**Localization**][Kapture: Robust Image Retrieval-based Visual Localization using Kapture](https://github.com/naver/kapture), arXiv 2020, **[[PDF](https://arxiv.org/abs/2007.13867)]**, 基于3D模型的视觉定位，局部特征支持[R2D2](http://xxx.itp.ac.cn/abs/1906.06195),[D2-Net](http://xxx.itp.ac.cn/abs/1905.03561),全局特征为[AP-GeM](https://europe.naverlabs.com/research/computer-vision-research-naver-labs-europe/learning-visual-representations/deep-image-retrieval/),另外提出了一种灵活的数据组织格式Kapture，能够轻易地支持导入/出数据到现有的SfM软件

- [**Localization**][CamOdoCal: Automatic Intrinsic and Extrinsic Calibration of a Rig with Multiple Generic Cameras and Odometry](https://github.com/hengli/camodocal), RSJ International Conference on Intelligent Robots & Systems 2013, **[[PDF](https://sci-hub.do/10.1109/iros.2013.6696592)]**

- [**Localization**][Night-to-Day Image Translation for Retrieval-based Localization](https://github.com/AAnoosheh/ToDayGAN), arXiv 2018, **[[PDF](https://arxiv.org/abs/1809.09767)]**， 黑夜转白天准确视觉定位

- [**Localization**][DSAC: DSAC – Differentiable RANSAC for Camera Localization](https://github.com/cvlab-dresden/DSAC), CVPR 2017, **[[PDF](https://arxiv.org/abs/1611.05705)]**, **[[Homepage](https://hci.iwr.uni-heidelberg.de/vislearn/research/scene-understanding/pose-estimation/#DSAC)]**

- [**Localization**][ESAC: Expert Sample Consensus Applied to Camera Re-Localization](https://github.com/vislearn/esac), ICCV 2019, **[[PDF](https://arxiv.org/abs/1908.02484)]**, **[[Homepage](https://hci.iwr.uni-heidelberg.de/vislearn/research/scene-understanding/pose-estimation/#ICCV19)]**

- [**Localization**][DIFL-FCL：Retrieval-based Localization Based on Domain-invariant Feature Learning under Changing Environments](https://github.com/HanjiangHu/DIFL-FCL), IROS 2019, **[[PDF](https://arxiv.org/abs/1909.10184)]**

- [**Localization**][Visual Localization Under Appearance Change: A Filtering Approach](https://github.com/dadung/Visual-Localization-Filtering), DICTA 2019, **[[PDF](https://arxiv.org/abs/1811.08063)]**

- [**Localization**][A Generative Map for Image-based Camera Localization](https://github.com/Mingpan/generative_map), 2019, **[[PDF](https://arxiv.org/abs/1902.11124)]**，视觉定位

- [**Localization**][DISAM: Domain-invariant Similarity Activation Map Metric Learning for Retrieval-based Long-term Visual Localization](https://github.com/HanjiangHu/DISAM), IROS 2019, **[[PDF](https://arxiv.org/abs/2009.07719)]**，基于图像召回的视觉定位

- [**Localization**][RGB2LIDAR: Towards Solving Large-Scale Cross-Modal Visual Localization](https://github.com/niluthpol/RGB2LIDAR), ACM MM 2020, **[[PDF](https://arxiv.org/abs/2009.05695)]**，在LIDAR地图中用RGB定位

- [**Localization**][Multi-Process Fusion: Visual Place Recognition Using Multiple Image Processing Methods](https://github.com/StephenHausler/Multi-Process-Fusion), IEEE RAL 2019, **[[PDF](https://arxiv.org/abs/1903.03305)]**

- [**Localization**][Learning Two-View Correspondences and Geometry Using Order-Aware Network](https://github.com/zjhthu/OANet), ICCV 2019, **[[PDF](https://arxiv.org/abs/1908.04964)]**

- [**L-SLAM**][LeGO-LOAM: Lightweight and Ground-Optimized Lidar Odometry and Mapping on Variable Terrain](https://github.com/RobustFieldAutonomyLab/LeGO-LOAM), IROS 2018, **[[PDF](https://sci-hub.do/10.1109/iros.2018.8594299)]**

- [**SfM**][Multi-View Optimization of Local Feature Geometry](https://github.com/mihaidusmanu/local-feature-refinement), ECCV 2020, **[[PDF](https://arxiv.org/abs/2003.08348)]**, **[[Homepage](https://dsmn.ml/publications/mvolfg.html)]**, **[[Video](https://www.youtube.com/watch?v=zBbIFxMGs3A)]**

- [**VIO**][Robust and Efficient Visual-Inertial Odometry with Multi-plane Priors](https://github.com/zju3dv/PVIO), PRCV 2019, **[[PDF](http://www.cad.zju.edu.cn/home/gfzhang/projects/prcv2019-planeVIO.pdf)]**， 多平面先验VI里程计

- [**Relocalization**][Online Visual Place Recognition via Saliency Re-identification](https://github.com/wh200720041/SRLCD), IROS 2020, **[[PDF](https://arxiv.org/abs/2007.14549)]**, **[[Homepage](https://wanghan.pro/)]**

- [**SLAM**][DXSLAM: A Robust and Efficient Visual SLAM System with Deep Features](https://github.com/ivipsourcecode/dxslam), arXiv 2020, **[[PDF](https://arxiv.org/abs/2008.05416)]**

- [**Feature**][Learning Feature Descriptors using Camera Pose Supervision](https://github.com/qianqianwang68/caps), ECCV 2020, **[[PDF](https://arxiv.org/abs/2004.13324)]**, **[[Homepage](https://qianqianwang68.github.io/CAPS/)]**

- [**Feature**][Efficient adaptive non-maximal suppression algorithms for homogeneous spatial keypoint distribution](https://github.com/BAILOOL/ANMS-Codes),Pattern Recognition Letters 2019，特征点平均分布

- [**VIO**][ALVIO: Adaptive Line and Point Feature-based Visual Inertial Odometry for Robust Localization in Indoor Environments](https://github.com/ankh88324/ALVIO), 点+线特征

- [**SLAM**][ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM](https://github.com/UZ-SLAMLab/ORB_SLAM3), **[[PDF](https://arxiv.org/abs/2007.11898)]**

- [**SLAM**][LIO-SAM](https://github.com/TixiaoShan/LIO-SAM), 激光雷达IMU紧耦合SLAM

- [**Tool**][Robotics Toolbox for Python](https://github.com/petercorke/robotics-toolbox-python),  a Python implementation of the [Robotics Toolbox for MATLAB®](https://github.com/petercorke/robotics-toolbox-matlab)

- [**Matching**][LISRD](https://github.com/rpautrat/LISRD),ECCV 2020, **[[PDF](https://arxiv.org/abs/2007.08988)]**，在线局部不变特征匹配！重要！

- [**Matching**][AdaLAM](https://github.com/cavalli1234/AdaLAM),特征匹配快速滤除外点

- [**Calib**][fisheye_pinhole_calib_demo](https://github.com/3DCVer/fisheye_pinhole_calib_demo), 包括鱼眼模型、针孔模型的相机标定，封装了自动编译、库的打包以及外部库的调用测试

- [**Calib**][SensorCalibration](https://github.com/FENGChenxi0823/SensorCalibration), IMU雷达标定

- [**VO**][Low-Drift Visual Odometry in Structured Environments by Decoupling Rotational and Translational Motion](https://github.com/PyojinKim/LPVO),ICRA 2018, **[[PDF](http://pyojinkim.com/download/papers/2018_ICRA.pdf)]**, 结构化环境中将旋转量与平移量进行分离优化

- [**VIO**][VIO-SLAM](https://github.com/iamwangyabin/VIO-SLAM), 从零开始手写VIO课后作业

- [**Matching**][TFMatch: Learning-based image matching in TensorFlow](https://github.com/lzx551402/tfmatch),TensorFlow 实现的 GeoDesc,ASLFeat以及ContextDesc

- [**Tutorial**][SLAM-BOOK](https://github.com/yanyan-li/SLAM-BOOK), 一本关于SLAM的书稿，清楚的介绍SLAM系统中的使用的几何方法和深度学习方法，持续更新中

- [**Loop Closing**][OverlapNet - Loop Closing for 3D LiDAR-based SLAM](https://github.com/PRBonn/OverlapNet), RSS 2020, **[[PDF](https://www.ipb.uni-bonn.de/wp-content/papercite-data/pdf/chen2020rss.pdf)]**, 3D激光雷达SLAM闭环

- [**SLAM**][VDO_SLAM](https://github.com/halajun/VDO_SLAM), RGB-D相机数据作为输入，实现追踪动态物体SLAM的功能, **[[PDF](https://arxiv.org/abs/2005.11052)]**

- [**SLAM**][orbslam-map-saving-extension](https://github.com/TUMFTM/orbslam-map-saving-extension)，在ORB-SLAM的基础上增加保存+加载地图功能

- [**Tutorial**][Modern Robotics: Mechanics, Planning, and Control Code Library](https://github.com/NxRLab/ModernRobotics), 现代机器人学, **[[Homepage](http://hades.mech.northwestern.edu/index.php/Modern_Robotics)]**

- [**Matching**][image-matching-benchmark-baselines](https://github.com/vcg-uvic/image-matching-benchmark-baselines), 图像特征匹配挑战赛主页

- [**Matching**][GraphLineMatching](https://github.com/mameng1/GraphLineMatching)

- [**Matching**][Locality Preserving Matching](https://github.com/jiayi-ma/LPM), IJCAI 2017, **[[PDF](https://ai.tencent.com/ailab/media/publications/YuanGao_IJCAI2017_LocalityPreservingMatching.pdf)]**

- [**IMU**][IMUOrientationEstimator](https://github.com/ydsf16/IMUOrientationEstimator)

- [**Feature**][BEBLID: Boosted Efficient Binary Local Image Descriptor](https://github.com/iago-suarez/BEBLID)

- [**Relocalization**][KFNet: Learning Temporal Camera Relocalization using Kalman Filtering](https://github.com/zlthinker/KFNet),CVPR 2020,**[[PDF](https://arxiv.org/abs/2003.10629)]**

- [**Matching**][image-matching-benchmark](https://github.com/vcg-uvic/image-matching-benchmark)

- [**Matching**][GMS: Grid-based Motion Statistics for Fast, Ultra-robust Feature Correspondence](https://github.com/JiawangBian/GMS-Feature-Matcher),CVPR 17 & IJCV 19,**[[PDF](http://jwbian.net/Papers/GMS_CVPR17.pdf)]**,**[[Project page](http://jwbian.net/gms)]**

- [**Reloc**][GN-Net-Benchmark](https://github.com/Artisense-ai/GN-Net-Benchmark), CVPR 2020,GN-Net: The Gauss-Newton Loss for Multi-Weather Relocalization, **[[PDF](https://arxiv.org/abs/1904.11932)]**,**[[Project page](http://vision.in.tum.de/gn-net)]**

- [**Matching**][SuperGluePretrainedNetwork](https://github.com/magicleap/SuperGluePretrainedNetwork), CVPR 2020, **[[PDF](https://arxiv.org/abs/1911.11763)]**, 划重点！2020年sota超大视角2D特征匹配，[Blog](https://www.vincentqin.tech/posts/superglue/)

- [**Feature**][D3Feat](https://github.com/XuyangBai/D3Feat), CVPR 2020, **[[PDF](https://arxiv.org/abs/2003.03164)]**

- [**Feature**][ASLFeat](https://github.com/lzx551402/ASLFeat), CVPR 2020, ASLFeat: Learning Local Features of Accurate Shape and Localization, **[[PDF](https://arxiv.org/abs/2003.10071)]**

- [**Feature**][GMS-Feature-Matcher](https://github.com/XuyangBai/D3Feat), CVPR 2018, GMS: Grid-based Motion Statistics for Fast, Ultra-robust Feature Correspondence, **[[PDF](http://jwbian.net/Papers/GMS_CVPR17.pdf)]**,**[[Project page](http://jwbian.net/gms)]**

- [**Feature**][D3Feat](https://github.com/XuyangBai/D3Feat), CVPR 2020, **[[PDF](https://arxiv.org/abs/2003.03164)]**

- [**Feature**][3DFeatNet](https://github.com/yewzijian/3DFeatNet), ECCV 2018, **[[PDF](https://arxiv.org/abs/1807.09413)]**

- [**Tutorial**][AutonomousDrivingCookbook](https://github.com/microsoft/AutonomousDrivingCookbook)，Scenarios, tutorials and demos for Autonomous Driving

- [**Tutorial**][SLAMPaperReading](https://github.com/PaoPaoRobot/SLAMPaperReading)，泡泡机器人北京线下SLAM论文分享资料

- [**Tutorial**][VIO_Tutotial_Course](https://github.com/lishuwei0424/VIO_Tutotial_Course)

- [**Tutorial**][VO-SLAM-Review](https://github.com/MichaelBeechan/VO-SLAM-Review)

- [**Tutorial**][VINS-Mono-code-annotation](https://github.com/QingSimon/VINS-Mono-code-annotation),VINS-Mono代码注释以及公式推导

- [**Tutorial**][VINS-Mono-Learning](https://github.com/ManiiXu/VINS-Mono-Learning),VINS-Mono代码注释

- [**Tutorial**][VINS-Course](https://github.com/HeYijia/VINS-Course),VINS-Mono code without Ceres or ROS

- [**Tutorial**][VIO-Doc](https://github.com/StevenCui/VIO-Doc),主流VIO论文推导及代码解析

- [**VO**][CNN-DSO](https://github.com/muskie82/CNN-DSO), Direct Sparse Odometry with CNN Depth Prediction

- [**VO**][fisheye-ORB-SLAM](https://github.com/lsyads/fisheye-ORB-SLAM), A real-time robust monocular visual SLAM system based on ORB-SLAM for fisheye cameras, without rectifying or cropping the input images

- [**VO**][ORB_Line_SLAM](https://github.com/robotseu/ORB_Line_SLAM), Real-Time SLAM with BoPLW Pairs for Stereo Cameras, with Loop Detection and Relocalization Capabilities

- [**VO**][DeepVO-pytorch](https://github.com/ChiWeiHsiao/DeepVO-pytorch.git), ICRA 2017 [DeepVO: Towards end-to-end visual odometry with deep Recurrent Convolutional Neural Networks](https://ieeexplore.ieee.org/document/7989236/)

- [**Calib**][CamOdomCalibraTool](https://github.com/MegviiRobot/CamOdomCalibraTool), The tool to calibrate extrinsic param between camera and wheel.

- [**Calib**][lidar_camera_calibration](https://github.com/heethesh/lidar_camera_calibration),[another version](https://github.com/ankitdhall/lidar_camera_calibration)

- [**Calib**][OdomLaserCalibraTool](https://github.com/MegviiRobot/OdomLaserCalibraTool.git)，相机与2D雷达标定

- [**Calib**][extrinsic_lidar_camera_calibration](https://github.com/UMich-BipedLab/extrinsic_lidar_camera_calibration), LiDARTag: A Real-Time Fiducial Tag using Point Clouds, arXiv 2019, **[[PDF](https://arxiv.org/abs/1908.10349)]**

- [**Calib**][velo2cam_calibration](https://github.com/beltransen/velo2cam_calibration), Automatic Calibration algorithm for Lidar-Stereo camera, **[[Project page](http://wiki.ros.org/velo2cam_calibration)]**

- [**Dataset**][IRS: A Large Synthetic Indoor Robotics Stereo Dataset for Disparity and Surface Normal Estimation](https://github.com/HKBU-HPML/IRS.git)

- [**Tools**][averaging-quaternions](https://github.com/christophhagen/averaging-quaternions),四元数平均

---
分割线，以下是2019年的星标项目，上面是2020年新星标的。

- [R2D2: Reliable and Repeatable Detector and Descriptor](https://github.com/naver/r2d2),NeurIPS 2019,**[[PDF](https://arxiv.org/abs/1906.06195)]**,**[[Project page](https://europe.naverlabs.com/research/publications/r2d2-reliable-and-repeatable-detectors-and-descriptors-for-joint-sparse-local-keypoint-detection-and-feature-extraction/)]**，深度学习特征点+描述子

- [Semantic_SLAM](https://github.com/1989Ryan/Semantic_SLAM),语义SLAM：ROS + ORB SLAM + PSPNet101

- [PlaceRecognition-LoopDetection](https://github.com/BAILOOL/PlaceRecognition-LoopDetection), Light-weight place recognition and loop detection using road markings

- [DOOR-SLAM: Distributed, online, and outlier resilient SLAM for robotic teams](https://github.com/MISTLab/DOOR-SLAM),**[[PDF](https://arxiv.org/abs/1909.12198)]**,**[[Project page](https://mistlab.ca/DOOR-SLAM/)]**，多机器人协作SLAM，增强了场景的适用性

- [awesome-local-global-descriptor](https://github.com/shamangary/awesome-local-global-descriptor), 超详细深度学习特征点描述子集合，需要重点关注一下这个repo

- [GIFT: Learning Transformation-Invariant Dense Visual Descriptors via Group CNNs](https://github.com/zju3dv/GIFT), NeurIPS 2019，**[[PDF](https://arxiv.org/abs/1911.05932)]**, **[[Project page](https://zju3dv.github.io/GIFT/)]**，浙大CAD+商汤联合实验室出品，利用Group CNN来改进superpoint描述子（仅描述，特征点提取可任意选择），可以大幅度增强视角变化时的特征点复检率与匹配点数

- [Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filters](https://github.com/axelBarroso/Key.Net),ICCV 2019, **[[PDF](https://arxiv.org/abs/1904.00889)]**, 深度学习特征点

- [Self-Supervised 3D Keypoint Learning for Ego-motion Estimation](https://github.com/TRI-ML/KP3D),**[[PDF](https://arxiv.org/abs/1912.03426)]**,**[[Youtube](https://www.youtube.com/watch?v=4hFhSD8QUPM)]**, 深度学习特征点

- [VINS-Mono-Optimization](https://github.com/Jichao-Peng/VINS-Mono-Optimization), 实现点线紧耦合优化的VINS-Mono

- [msckf_vio注释版本](https://github.com/PetWorm/msckf_vio_zhushi)

- [NetVLAD-pytorch](https://github.com/lyakaap/NetVLAD-pytorch), NetVLAD场景识别的pytorch实现

- [High-Precision Localization Using Ground Texture (Micro-GPS)](http://microgps.cs.princeton.edu/),ECCV 2018,**[[PDF](https://arxiv.org/abs/1710.10687)]**,**[[Project page](http://microgps.cs.princeton.edu/)]**,**[[code](http://microgps.cs.princeton.edu/data/micro-gps-cpp-master.zip)]**，地向（摄像机朝向地面）SLAM，获得高精度重定位效果。

- [PlaneSLAM](https://github.com/LRMPUT/PlaneSLAM), Paper: “On the Representation of Planes for Efficient Graph-based SLAM with High-level Features”

- [XIVO: X Inertial-aided Visual Odometry and Sparse Mapping](https://github.com/ucla-vision/xivo), an open-source repository for visual-inertial odometry/mapping.

- [DeepTAM](https://github.com/lmb-freiburg/deeptam),ECCV 2018,**[[PDF](https://arxiv.org/pdf/1808.01900.pdf)]**,**[[Project page](https://lmb.informatik.uni-freiburg.de/people/zhouh/deeptam/)]**,a learnt system for keyframe-based dense camera tracking and mapping.

- [iRotAvg, Why bundle adjust?](https://github.com/ajparra/iRotAvg),ICRA 2019,**[[PDF](https://cs.adelaide.edu.au/~aparra/publication/parra19_icra/)]**
- [Tactical Rewind: Self-Correction via Backtracking in Vision-and-Language Navigation](https://github.com/Kelym/FAST),CVPR 2019,**[[PDF](http://openaccess.thecvf.com/content_CVPR_2019/html/Ke_Tactical_Rewind_Self-Correction_via_Backtracking_in_Vision-And-Language_Navigation_CVPR_2019_paper.html)]**，视觉+语言导航
- [DOOR-SLAM](https://github.com/MISTLab/DOOR-SLAM)
- [An Evaluation of Feature Matchers for Fundamental Matrix Estimation](https://github.com/JiawangBian/FM-Bench),BMVC 2019,**[[PDF](https://jwbian.net/Papers/FM_BMVC19.pdf)]**,**[[Project Page](http://jwbian.net/fm-bench)]**，特征匹配
- [A Tightly Coupled 3D Lidar and Inertial Odometry and Mapping Approach](https://github.com/hyye/lio-mapping),ICRA 2019,**[[PDF](https://arxiv.org/abs/1904.06993)]**,**[[Project Page](https://sites.google.com/view/lio-mapping)]**，紧耦合雷达+IMU SLAM
- [On the Representation of Planes for Efficient Graph-based SLAM with High-level Features](https://github.com/LRMPUT/PlaneSLAM),利用平面信息的SLAM
- [Visual Odometry Revisited: What Should Be Learnt?](https://github.com/Huangying-Zhan/DF-VO),arXiv 2019,**[[PDF](https://arxiv.org/abs/1909.09803)]**, 深度学习深度+光流进行VO
- [RF-Net: An End-to-End Image Matching Network based on Receptive Field](https://github.com/Xylon-Sean/rfnet),CVPR 2019,**[[PDF](https://arxiv.org/abs/1906.00604)]**, 端到端图像匹配
- [Fast-Planner](https://github.com/HKUST-Aerial-Robotics/Fast-Planner),IEEE Robotics and Automation Letters (RA-L), 2019,**[[PDF](https://ieeexplore.ieee.org/document/8758904)]**, 无人机轨迹生成
- [A general and flexible factor graph non-linear least square optimization framework](https://github.com/dongjing3309/minisam),CoRR 2019,**[[PDF](http://arxiv.org/abs/1909.00903)]**,**[[Project Page](https://minisam.readthedocs.io/)]**
- [Demo for Kalman filter in ranging system](https://github.com/gao-ouyang/demo_for_kalmanFilter),卡尔曼滤波原理演示
- [A Holistic Visual Place Recognition Approach using Lightweight CNNs for Severe ViewPoint and Appearance Changes](https://github.com/Ahmedest61/CNN-Region-VLAD-VPR)，场景识别（外观与视角变化时）,[训练和部署源码](https://github.com/ethz-asl/hierarchical_loc)
- [SIPs: Succinct Interest Points from Unsupervised Inlierness Probability Learning](https://github.com/uzh-rpg/sips2_open),3D Vision (3DV) 2019,**[[PDF](https://arxiv.org/abs/1805.01358)]**，RPG实验室出品，深度学习特征点（有特征描述子）

- [Matching Features Without Descriptors: Implicitly Matched Interest Points](https://github.com/uzh-rpg/imips_open),BMVC 2019,**[[PDF](http://rpg.ifi.uzh.ch/docs/BMVC19_Cieslewski.pdf)]**,RPG实验室出品，无需特征描述即可进行特征匹配

- [Learning Lightweight Lane Detection CNNs by Self Attention Distillation (ICCV 2019)](https://github.com/cardwing/Codes-for-Lane-Detection),ICCV 2019,**[[PDF](https://arxiv.org/abs/1908.00821)]**，深度学习道路检测

- [Awesome SLAM Datasets](https://github.com/youngguncho/awesome-slam-datasets),史上最全SLAM数据集， **[公众号说明: 最全 SLAM 开源数据集](https://mp.weixin.qq.com/s/BzcghUnXTR9RQqA3Pc9MhA)**

- [GNSS-INS-SIM](https://github.com/Aceinna/gnss-ins-sim),惯导融合模拟器，支持IMU数据，轨迹生成等

- [Multi-Sensor Combined Navigation Program(GNSS, IMU, Camera and so on) 多源多传感器融合定位 GPS/INS组合导航](https://github.com/2013fangwentao/Multi-Sensor-Combined-Navigation)

- [SOSNet: Second Order Similarity Regularization for Local Descriptor Learning](https://github.com/scape-research/SOSNet),CVPR 2019,**[[Project page]](https://research.scape.io/sosnet/)** **[[Paper]](https://arxiv.org/abs/1904.05019)** **[[Poster]](imgs/sosnet-poster.pdf)** **[[Slides]](imgs/sosnet-oral.pdf)**，一种深度学习特征描述子

- [Look No Deeper: Recognizing Places from Opposing Viewpoints under Varying Scene Appearance using Single-View Depth Estimation](https://github.com/oravus/seq2single),ICRA 2019,**[[PDF](https://arxiv.org/abs/1902.07381)]**,利用深度图像实现了大视角长时间的场景识别（根据深度图筛选得到不同深度层次的特征点然后与当前帧进行匹配，提高了场景召回率）

- [CALC2.0](https://github.com/rpng/calc2.0),Convolutional Autoencoder for Loop Closure 2.0,用于闭环检测

- [SegMap](https://github.com/ethz-asl/segmap),RSS 2018,**[[PDF](http://www.roboticsproceedings.org/rss14/p03.pdf)]**, 一种基于3D线段的地图表示，可用于场景识别/机器人定位/环境重建等

- [MSCKF_VIO](https://github.com/cggos/msckf_vio_cg), a stereo version of MSCKF，基于MSCKF的双目VIO

- [NetVLAD: CNN architecture for weakly supervised place recognition](https://github.com/Relja/netvlad)，CVPR 2016, CNN框架弱监督学习场景识别,**[[Project Page](https://www.di.ens.fr/willow/research/netvlad/)]**

- [easy_handeye](https://github.com/IFL-CAMP/easy_handeye),Simple, straighforward ROS library for hand-eye calibration

- [SuperPoint-SLAM](https://github.com/KinglittleQ/SuperPoint_SLAM),利用SuperPoint替换ORB特征点

- [PyRobot: An Open Source Robotics Research Platform](https://github.com/facebookresearch/pyrobot)

- [From Coarse to Fine: Robust Hierarchical Localization at Large Scale with HF-Net](https://github.com/ethz-asl/hfnet),**[[PDF](https://arxiv.org/abs/1812.03506)]**

- [Super fast implementation of ICP in CUDA](https://github.com/mp3guy/ICPCUDA)

- [ A generic interface for disparity map and pointcloud insertion](https://github.com/ethz-asl/volumetric_mapping)

- [SPHORB: A Fast and Robust Binary Feature on the Sphere](https://github.com/tdsuper/SPHORB),International Journal of Computer Vision 2015,**[[PDF](http://scs.tju.edu.cn/~lwan/paper/SPHORB/pdf/SPHORB-final-small.pdf)]**,**[[Project Page](http://scs.tju.edu.cn/~lwan/paper/SPHORB/SPHORB.html)]**

- [BADSLAM: Bundle Adjusted Direct RGB-D SLAM](https://github.com/ETH3D/badslam),CVPR 2019,**[[PDF](http://openaccess.thecvf.com/content_CVPR_2019/papers/Schops_BAD_SLAM_Bundle_Adjusted_Direct_RGB-D_SLAM_CVPR_2019_paper.pdf)]**

- [High Speed and High Dynamic Range Video with an Event Camera](https://github.com/uzh-rpg/rpg_e2vid),arXiv,**[[PDF](http://rpg.ifi.uzh.ch/docs/arXiv19_Rebecq.pdf)]**,**[[Project Page](http://rpg.ifi.uzh.ch/E2VID.html)]**

- [Awesome-VIO](https://github.com/PaoPaoRobot/Awesome-VIO),Discuss about VIO in PaoPaoRobot group
- [GyroAllan](https://github.com/XinLiGH/GyroAllan),陀螺仪随机误差的 Allan 方差分析, [Another version](https://github.com/rpng/kalibr_allan)

- [Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and Monocular Camera](https://github.com/fangchangma/self-supervised-depth-completion),ICRA 2019,**[[PDF](https://arxiv.org/pdf/1807.00275.pdf)]**, 优化LiDAR以及单目得到的深度图
- [PlaneRCNN: 3D Plane Detection and Reconstruction from a Single Image](https://github.com/NVlabs/planercnn),CVPR 2019,**[[PDF](https://arxiv.org/pdf/1812.04072.pdf)]**,**[[Project Page](https://research.nvidia.com/publication/2019-06_PlaneRCNN)]**,通过单幅图像进行3D平面检测以及重建
- [DBow3](https://github.com/kokerf/DBow3),注释版的DBow3代码
- [Visual-Inertial Mapping with Non-Linear Factor Recovery](https://github.com/VladyslavUsenko/basalt-mirror),**[[PDF](https://arxiv.org/abs/1904.06504)]**,**[[Project Page](https://vision.in.tum.de/research/vslam/basalt)]**, 时空联合的VIO优化方案
- [ICRA2019-paper-list](https://github.com/PaoPaoRobot/ICRA2019-paper-list),ICRA 2019论文列表（泡泡机器人出品暂时无链接）
- [Fast Cylinder and Plane Extraction from Depth Cameras for Visual Odometry](https://github.com/pedropro/CAPE), IROS 2018,**[[PDF](https://arxiv.org/abs/1803.02380)]**,利用深度图进行圆柱检测以及平面检测进行VO
- [Solutions to assignments of Robot Mapping Course WS 2013/14 by Dr. Cyrill Stachniss at University of Freiburg](https://github.com/kiran-mohan/SLAM-Algorithms-Octave),SLAM算法学习课后作业答案
- [Direct sparse odometry combined with stereo cameras and IMU](https://github.com/RonaldSun/VI-Stereo-DSO),双目DSO+IMU
- [Direct Sparse Odometry with Stereo Cameras](https://github.com/HorizonAD/stereo_dso),双目DSO
- [Python binding of SLAM graph optimization framework g2o](https://github.com/uoip/g2opy),python版本的g2o实现
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://github.com/rpautrat/SuperPoint), CVPR 2018, **[[Paper](https://arxiv.org/abs/1712.07629)]**, 深度学习描述子+描述
- [ContextDesc: Local Descriptor Augmentation with Cross-Modality Context](https://github.com/lzx551402/contextdesc), CVPR 2019, **[[Paper](https://arxiv.org/abs/1904.04084)]**, 深度学习描述子
- [D2-Net: A Trainable CNN for Joint Description and Detection of Local Features](https://github.com/mihaidusmanu/d2-net), CVPR 2019, **[[Paper](https://arxiv.org/abs/1905.03561)]**, **[[Project Page](https://dsmn.ml/publications/d2-net.html)]**, 深度学习关键点+描述
- [ROS interface for ORBSLAM2](https://github.com/ethz-asl/orb_slam_2_ros),ROS版本的ORBSLAM2
- [CNN-SVO: Improving the Mapping in Semi-Direct Visual Odometry Using Single-Image Depth Prediction](https://github.com/yan99033/CNN-SVO)， **[[Paper](https://arxiv.org/pdf/1810.01011.pdf)]**
- [VINS-Mono-Learning](https://github.com/ManiiXu/VINS-Mono-Learning)，代码注释版VINS-Mono，初学者学习
- [OpenVSLAM: Versatile Visual SLAM Framework](https://github.com/xdspacelab/openvslam), **[[Project Page](https://openvslam.readthedocs.io/)]**
- [RESLAM: A real-time robust edge-based SLAM system](https://github.com/fabianschenk/RESLAM), ICRA 2019, **[[Paper](https://github.com/fabianschenk/fabianschenk.github.io/raw/master/files/schenk_icra_2019.pdf)]**
- [PL-SLAM: a Stereo SLAM System through the Combination of Points and Line Segments](https://github.com/rubengooj/pl-slam), **[[Paper](https://arxiv.org/abs/1705.09479)]**，线特征SLAM
- [Good Line Cutting: towards Accurate Pose Tracking of Line-assisted VO/VSLAM](https://github.com/YipuZhao/GF_PL_SLAM), ECCV 2018, **[[Project Page](https://sites.google.com/site/zhaoyipu/good-feature-visual-slam)]**, 改进的PL-SLAM
- [Spherical Regression: Learning Viewpoints, Surface Normals and 3D Rotations on n-Spheres](https://github.com/leoshine/Spherical_Regression), CVPR 2019, **[[Paper](http://arxiv.org/abs/1904.05404)]**
- [svo_edgelet](https://github.com/icsl-Jeon/traj_gen_vis), 在线轨迹生成
- [Drone SLAM project for Caltech's ME 134 Autonomy class](https://github.com/TimboKZ/caltech_samaritan), **[[PDF](https://github.com/TimboKZ/caltech_samaritan/blob/master/CS134_Final_Project_Report.pdf)]**
- [Online Trajectory Generation of a MAV for Chasing a Moving Target in 3D Dense Environments](https://github.com/icsl-Jeon/traj_gen_vis), **[[Paper](https://arxiv.org/pdf/1904.03421.pdf)]**
- [PythonRobotics](https://github.com/AtsushiSakai/PythonRobotics),**[[Paper](https://arxiv.org/abs/1808.10703)]**, [CppRobotics](https://github.com/onlytailei/CppRobotics)
- [Bundle adjustment demo using Ceres Solver](https://github.com/izhengfan/ba_demo_ceres),  **[[Blog](https://fzheng.me/2018/01/23/ba-demo-ceres/)]**, ceres实现BA
- [CubeSLAM: Monocular 3D Object Detection and SLAM](https://github.com/shichaoy/cube_slam), **[[Paper](https://arxiv.org/abs/1806.00557)]**
- [PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud](https://github.com/sshaoshuai/PointRCNN), CVPR 2019, **[[Paper](https://arxiv.org/abs/1812.04244)]**
- [GIST-Global Image Descriptor](https://github.com/nrupatunga/GIST-global-Image-Descripor), GIST描述子
- [mav voxblox planning](https://github.com/ethz-asl/mav_voxblox_planning), MAV planning tools using voxblox as the map representation.
- [Python Kalman Filter](https://github.com/zziz/kalman-filter), 30行实现卡尔曼滤波
- [vicalib](https://github.com/arpg/vicalib), 视觉惯导系统标定工具
- [BreezySLAM](https://github.com/simondlevy/BreezySLAM), 基于雷达的SLAM，支持Python(&Matlab, C++, and Java)
- [Probabilistic-Robotics](https://github.com/Yvon-Shong/Probabilistic-Robotics), 《概率机器人》中文版，书和课后习题
- [Stanford Self Driving Car Code](https://github.com/emmjaykay/stanford_self_driving_car_code), **[[Paper](http://robots.stanford.edu/papers/junior08.pdf)]**, 斯坦福自动驾驶车代码
- [Udacity Self-Driving Car Engineer Nanodegree projects](https://github.com/ndrplz/self-driving-car)
- [Artificial Intelligence in Automotive Technology](https://github.com/TUMFTM/Lecture_AI_in_Automotive_Technology), TUM自动驾驶技术中的人工智能课程
- [DeepMatchVO: Beyond Photometric Loss for Self-Supervised Ego-Motion Estimation](https://github.com/hlzz/DeepMatchVO),ICRA 2019, **[[Paper](https://arxiv.org/abs/1902.09103)]**
- [GSLAM: A General SLAM Framework and Benchmark](https://github.com/zdzhaoyong/GSLAM), CVPR 2019, **[[Paper](https://arxiv.org/abs/1902.07995)]**, 集成了各种传感器输入的SLAM统一框架
- [Visual-Odometric Localization and Mapping for Ground Vehicles Using SE(2)-XYZ Constraints](https://github.com/izhengfan/se2lam)，ICRA 2019,基于SE(2)-XYZ约束的VO系统
- [Simple bag-of-words loop closure for visual SLAM](https://github.com/nicolov/simple_slam_loop_closure), **[[Blog](https://nicolovaligi.com/bag-of-words-loop-closure-visual-slam.html)]**, 回环
- [FBOW (Fast Bag of Words), an extremmely optimized version of the DBow2/DBow3 libraries](https://github.com/rmsalinas/fbow),优化版本的DBow2/DBow3
- [Multi-State Constraint Kalman Filter (MSCKF) for Vision-aided Inertial Navigation(master's thesis)](https://github.com/tomas789/tonav)
- [MSCKF](https://github.com/yuzhou42/MSCKF), MSCKF中文注释版
- [Calibration algorithm for a camera odometry system](https://github.com/hbtang/calibcamodo), VO系统的标定程序
- [Modified version of VINS-Mono](https://github.com/cggos/vins_mono_cg), 注释版本VINS Mono
- [Extreme Relative Pose Estimation for RGB-D Scans via Scene Completion](https://github.com/zhenpeiyang/RelativePose),**[[Paper](https://arxiv.org/abs/1901.00063)]**
- [Implementation of EPnP algorithm with Eigen](https://github.com/jessecw/EPnP_Eigen),利用Eigen编写的EPnP
- [Real-time SLAM system with deep features](https://github.com/jiexiong2016/GCNv2_SLAM), 深度学习描述子(ORB vs. GCNv2)
- [Unsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature Reconstruction](https://github.com/Huangying-Zhan/Depth-VO-Feat), CVPR 2018, 无监督单目深度恢复以及VO
- [ORB-SLAM-windows](https://github.com/Phylliida/orbslam-windows), Windows版本的ORB-SLAM
- [StructVIO : Visual-inertial Odometry with Structural Regularity of Man-made Environments](https://github.com/danping/structvio),**[[Project Page](http://drone.sjtu.edu.cn/dpzou/project/structvio.html)]**
- [KalmanFiltering](https://github.com/irvingzhang/KalmanFiltering), 各种卡尔曼滤波器的demo
- [Stereo Odometry based on careful Feature selection and Tracking](https://github.com/ZhenghaoFei/visual_odom), **[[Paper](https://lamor.fer.hr/images/50020776/Cvisic2017.pdf)]**, C++ OpenCV实现SOFT
- [Visual SLAM with RGB-D Cameras based on Pose Graph Optimization](https://github.com/dzunigan/zSLAM)
- [Multi-threaded generic RANSAC implemetation](https://github.com/drsrinathsridhar/GRANSAC), 多线程RANSAC
- [Visual Odometry with Drift-Free Rotation Estimation Using Indoor Scene Regularities](https://github.com/PyojinKim/OPVO), BMVC 2017, **[[Project Page](http://pyojinkim.me/pub/Visual-Odometry-with-Drift-Free-Rotation-Estimation-Using-Indoor-Scene-Regularities/)]**，利用平面正交信息进行VO
- [ICE-BA](https://github.com/baidu/ICE-BA), CVPR 2018, **[[Paper](http://openaccess.thecvf.com/content_cvpr_2018/papers/Liu_ICE-BA_Incremental_Consistent_CVPR_2018_paper.pdf)]**
- [GraphSfM: Robust and Efficient Graph-based Structure from Motion](https://github.com/AIBluefisher/GraphSfM), **[[Project Page](https://aibluefisher.github.io/GraphSfM/)]**
- [LOAM_NOTED](https://github.com/cuitaixiang/LOAM_NOTED), loam中文注解版
- [Divide and Conquer: Effcient Density-Based Tracking of 3D Sensors in Manhattan Worlds](https://github.com/Ethan-Zhou/MWO),ACCV 2016,**[[Project Page](http://users.cecs.anu.edu.au/~u5535909/)]**,曼哈顿世界利用深度传感器进行旋转量平移量分离优化
- [Real-time Manhattan World Rotation Estimation in 3D](https://github.com/jstraub/rtmf),IROS 2015,实时曼哈顿世界旋转估计

- [Event-based Vision Resources](https://github.com/uzh-rpg/event-based_vision_resources)，关于事件相机的资源
- [AutonomousVehiclePaper](https://github.com/DeepTecher/AutonomousVehiclePaper)，无人驾驶相关论文速递
- [Segmentation.X](https://github.com/wutianyiRosun/Segmentation.X), Segmentation相关论文&代码
- [CVPR-2019](https://github.com/amusi/CVPR2019-Code), CVPR 2019 论文开源项目合集
- [awesome-slam](https://github.com/kanster/awesome-slam), SLAM合集
- [awesome-visual-slam](https://github.com/tzutalin/awesome-visual-slam), 视觉SLAM合集
- [Papers with code](https://github.com/zziz/pwc), 周更论文with代码
- [Awesome Human Pose Estimation](https://github.com/cbsudux/awesome-human-pose-estimation),[awesome-object-pose](https://github.com/nkalavak/awesome-object-pose), 位姿估计合集
- [MVision](https://github.com/Ewenwan/MVision), 大礼包：机器人视觉 移动机器人 VS-SLAM ORB-SLAM2 深度学习目标检测 yolov3 行为检测 opencv PCL 机器学习 无人驾驶

## Pose/Object tracking

- [Unsupervised person re-identification by soft multilabel learning](https://github.com/KovenYu/MAR),CVPR 2019,  **[[Paper](https://kovenyu.com/papers/2019_CVPR_MAR.pdf)]**

- [FCOS: Fully Convolutional One-Stage Object Detection](https://github.com/tianzhi0549/FCOS),ICCV 2019,  **[[Paper](https://arxiv.org/abs/1904.01355)]**

- [Hand Detection and Orientation Estimation](https://github.com/yangli18/hand_detection)
- [Spatial-Temporal Person Re-identification](https://github.com/Wanggcong/Spatial-Temporal-Re-identification),AAAI 2019,**[[Paper](https://arxiv.org/abs/1812.03282)]**
- [A tiny, friendly, strong pytorch implement of person re-identification baseline. **Tutorial**](https://github.com/layumi/Person_reID_baseline_pytorch),CVPR 2019,  **[[Paper](https://arxiv.org/abs/1904.07223)]**

- [Progressive Pose Attention for Person Image Generation](https://github.com/tengteng95/Pose-Transfer),CVPR 2019,**[[Paper](http://arxiv.org/abs/1904.03349)]**

- [FSA-Net: Learning Fine-Grained Structure Aggregation for Head Pose Estimation from a Single Image](https://github.com/shamangary/FSA-Net), CVPR 2019,**[[Paper](https://github.com/shamangary/FSA-Net/blob/master/0191.pdf)]**
- [An unoffical implemention for paper "Fast Human Pose Estimation"](https://github.com/yuanyuanli85/Fast_Human_Pose_Estimation_Pytorch), CVPR 2019,**[[Paper](https://arxiv.org/abs/1811.05419)]**
- [Real-time single person pose estimation for Android and iOS](https://github.com/edvardHua/PoseEstimationForMobile),手机端实现人体位姿估计
- [Basics of 2D and 3D Human Pose Estimation](https://github.com/cbsudux/Human-Pose-Estimation-101),人体姿态估计入门
- [Libra R-CNN: Towards Balanced Learning for Object Detection](https://github.com/OceanPang/Libra_R-CNN)
- [High-resolution networks (HRNets) for object detection](https://github.com/HRNet/HRNet-Object-Detection), **[[Paper](https://arxiv.org/pdf/1904.04514.pdf)]**
- [Learning Correspondence from the Cycle-Consistency of Time](https://github.com/xiaolonw/TimeCycle), CVPR 2019, **[[Paper](https://arxiv.org/abs/1903.07593)]**
- [PVNet: Pixel-wise Voting Network for 6DoF Pose Estimation](https://github.com/zju3dv/pvnet), CVPR 2019, **[[Paper](https://arxiv.org/abs/1812.11788)], [[Project Page](https://zju3dv.github.io/pvnet)]**
- [Self-Supervised Learning of 3D Human Pose using Multi-view Geometry](https://github.com/mkocabas/EpipolarPose), CVPR 2018, **[[Paper](https://arxiv.org/abs/1903.02330)]**
- [PifPaf: Composite Fields for Human Pose Estimation](https://github.com/vita-epfl/openpifpaf), **[[Paper](https://arxiv.org/abs/1903.06593)]** 
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://github.com/leoxiaobin/deep-high-resolution-net.pytorch),CVPR 2019, **[[Paper](https://arxiv.org/pdf/1902.09212.pdf)]**, **[[Project Page](https://jingdongwang2017.github.io/Projects/HRNet/PoseEstimation.html)]**
- [PoseFlow: Efficient Online Pose Tracking)](https://github.com/YuliangXiu/PoseFlow), BMVC 2018, **[[Paper](https://arxiv.org/abs/1802.00977)]**
- [A Bottom-Up Clustering Approach to Unsupervised Person Re-identification](https://github.com/vana77/Bottom-up-Clustering-Person-Re-identification)，AAAI 2019, 重定位
- [Fast Online Object Tracking and Segmentation: A Unifying Approach](https://github.com/foolwood/SiamMask),CVPR 2019,**[[Paper](https://arxiv.org/abs/1812.05050)] [[Video](https://youtu.be/I_iOVrcpEBw)] [[Project Page](http://www.robots.ox.ac.uk/~qwang/SiamMask)]**
- [SimpleDet - A Simple and Versatile Framework for Object Detection and Instance Recognition](https://github.com/TuSimple/simpledet),**[[Paper](https://arxiv.org/abs/1903.05831)]**

## Depth/Disparity & Flow estimation

- [**Depth**][SemiGlobalMatching](https://github.com/ethan-li-coding/SemiGlobalMatching), SGM双目立体匹配算法完整实现，代码规范，注释丰富且清晰，CSDN同步教学

- [PointMVSNet: Point-based Multi-view Stereo Network](https://github.com/callmeray/PointMVSNet),ICCV 2019,**[[Paper](https://arxiv.org/abs/1908.04422)]**
- [DeepLiDAR](https://github.com/JiaxiongQ/DeepLiDAR),CVPR 2019, **[[Paper](http://openaccess.thecvf.com/content_CVPR_2019/papers/Qiu_DeepLiDAR_Deep_Surface_Normal_Guided_Depth_Prediction_for_Outdoor_Scene_CVPR_2019_paper.pdf)]**, 单张RGB图像+稀疏雷达数据进行室外场景深度估计
- [Real-Time Monocular Depth Estimation using Synthetic Data with Domain Adaptation via Image Style Transfer](https://github.com/atapour/monocularDepth-Inference),CVPR 2018, **[[Paper](http://breckon.eu/toby/publications/papers/abarghouei18monocular.pdf)]**
- [Learning Single-Image Depth from Videos using Quality Assessment Networks](https://github.com/princeton-vl/YouTube3D),CVPR 2019, **[[Paper](https://arxiv.org/abs/1806.09573)]**, **[[Project Page](http://www-personal.umich.edu/~wfchen/youtube3d/)]**

- [SCDA: Adapting Object Detectors via Selective Cross-Domain Alignment](https://github.com/WERush/SCDA),CVPR 2019, **[[Paper](http://openaccess.thecvf.com/content_CVPR_2019/papers/Zhu_Adapting_Object_Detectors_via_Selective_Cross-Domain_Alignment_CVPR_2019_paper.pdf)]**, **[[Project Page](http://zhuxinge.me/aboutme.html)]**

- [Learning monocular depth estimation infusing traditional stereo knowledge](https://github.com/fabiotosi92/monoResMatch-Tensorflow),CVPR 2019,**[[PDF](https://vision.disi.unibo.it/~ftosi/papers/monoResMatch.pdf)]**
- [HPLFlowNet: Hierarchical Permutohedral Lattice FlowNet for Scene Flow Estimation on Large-scale Point Clouds](https://github.com/laoreja/HPLFlowNet),CVPR 2019,**[[Paper](hhttps://web.cs.ucdavis.edu/~yjlee/projects/cvpr2019-HPLFlowNet.pdf)]**
- [GA-Net: Guided Aggregation Net for End-to-end Stereo Matching](https://github.com/feihuzhang/GANet),CVPR 2019,**[[Paper](https://arxiv.org/pdf/1904.06587.pdf)]**
- [DPSNet: End-to-end Deep Plane Sweep Stereo](https://github.com/sunghoonim/DPSNet),ICLR 2019,**[[Paper](https://openreview.net/pdf?id=ryeYHi0ctQ)]**
- [Fast Depth Densification for Occlusion-aware Augmented Reality](https://github.com/muskie82/AR-Depth-cpp), SIGGRAPH-Asia 2018, **[[Project Page](https://homes.cs.washington.edu/~holynski/publications/occlusion/index.html)]**,[another version](https://github.com/facebookresearch/AR-Depth)
- [Learning To Adapt For Stereo](https://github.com/CVLAB-Unibo/Learning2AdaptForStereo), CVPR 2019, **[[Paper](https://arxiv.org/pdf/1904.02957)]**
- [Pyramid Stereo Matching Network](https://github.com/JiaRenChang/PSMNet),**[[Paper](https://arxiv.org/abs/1803.08669)]** 
- [Bridging Stereo Matching and Optical Flow via Spatiotemporal Correspondence](https://github.com/lelimite4444/BridgeDepthFlow), **[[Paper](https://arxiv.org/abs/1905.09265)]**
- [Sparse Depth Completion](https://github.com/wvangansbeke/Sparse-Depth-Completion), **[[Paper](https://arxiv.org/pdf/1902.05356.pdf)]**, RGB图像辅助雷达深度估计
- [GASDA](https://github.com/sshan-zhao/GASDA), CVPR 2019, **[[Paper](https://sshan-zhao.github.io/papers/gasda.pdf)]**
- [MVSNet: Depth Inference for Unstructured Multi-view Stereo](https://github.com/xy-guo/MVSNet_pytorch), **[[Paper](https://arxiv.org/abs/1804.02505)]**, 非官方实现版本的MVSNet
- [Stereo R-CNN based 3D Object Detection for Autonomous Driving](https://github.com/HKUST-Aerial-Robotics/Stereo-RCNN), CVPR 2019, **[[Paper](https://arxiv.org/pdf/1902.09738.pdf)]**
- [Real-time self-adaptive deep stereo](https://github.com/CVLAB-Unibo/Real-time-self-adaptive-deep-stereo), CVPR 2019, **[[Paper](https://arxiv.org/abs/1810.05424)]**
- [High Quality Monocular Depth Estimation via Transfer Learning](https://github.com/ialhashim/DenseDepth),CVPR 2019, **[[Paper](https://arxiv.org/abs/1812.11941)]**, **[[Project Page](https://ialhashim.github.io/publications/index.html)]**
- [Group-wise Correlation Stereo Network](https://github.com/xy-guo/GwcNet),CVPR 2019, **[[Paper](https://arxiv.org/abs/1903.04025)]**
- [DeepMVS: Learning Multi-View Stereopsis](https://github.com/phuang17/DeepMVS), CVPR 2018,**[[Project Page](https://phuang17.github.io/DeepMVS/index.html)]**,多目深度估计
- [FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks](https://github.com/sampepose/flownet2-tf), CVPR 2017, 深度学习光流恢复
- [StereoVision-ADCensus](https://github.com/DLuensch/StereoVision-ADCensus),深度恢复代码集合(**ADCensus, SGBM, BM**)
- [SegStereo: Exploiting Semantic Information for Disparity Estimation](https://github.com/yangguorun/SegStereo), 探究语义信息在深度估计中的作用
- [Light Filed Depth Estimation using GAN](https://github.com/kuantingchen04/Light-Field-Depth-Estimation)，利用GAN进行光场深度恢复
- [EV-FlowNet: Self-Supervised Optical Flow for Event-based Cameras](https://github.com/daniilidis-group/EV-FlowNet),Proceedings of Robotics 2018,**[[Paper](https://arxiv.org/abs/1802.06898)]**
- [DF-Net: Unsupervised Joint Learning of Depth and Flow using Cross-Task Consistency](https://github.com/vt-vl-lab/DF-Net), ECCV 2018, **[[Paper](https://arxiv.org/abs/1809.01649)]**
- [GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose](https://github.com/yzcjtr/GeoNet), CVPR 2018, **[[Paper](https://arxiv.org/abs/1803.02276)]**

## 3D & Graphic
- [PRNet: Self-Supervised Learning for Partial-to-Partial Registration](https://github.com/WangYueFt/prnet),NeurIPS 2019
- [Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop](https://github.com/nkolot/SPIN),ICCV 2019, **[[Paper](https://arxiv.org/pdf/1909.12828.pdf)]** , **[[Project Page](https://www.seas.upenn.edu/~nkolot/projects/spin/)]** 
- [Cross View Fusion for 3D Human Pose Estimation](https://github.com/microsoft/multiview-human-pose-estimation-pytorch),ICCV 2019, **[[Paper](https://arxiv.org/abs/1909.01203)]** ,跨视角3D位姿估计
- [MVF-Net: Multi-View 3D Face Morphable Model Regression](https://github.com/Fanziapril/mvfnet),多视角3D人脸重建, **[[Paper](https://arxiv.org/abs/1904.04473)]** 
- [KillingFusion](https://github.com/saurabheights/KillingFusion)

- [ReFusion: 3D Reconstruction in Dynamic Environments for RGB-D Cameras Exploiting Residuals](https://github.com/PRBonn/refusion), **[[Paper](https://arxiv.org/pdf/1905.02082.pdf)]**

- [densebody_pytorch](https://github.com/Lotayou/densebody_pytorch), **[[Paper](https://arxiv.org/abs/1903.10153v3)]** 
- [Single-Image Piece-wise Planar 3D Reconstruction via Associative Embedding](https://github.com/svip-lab/PlanarReconstruction),CVPR 2019, **[[Paper](https://arxiv.org/pdf/1902.09777.pdf)]**, 单目3D重建
- [HorizonNet: Learning Room Layout with 1D Representation and Pano Stretch Data Augmentation](https://github.com/sunset1995/HorizonNet),CVPR 2019, **[[Paper](https://arxiv.org/abs/1901.03861)]**, 深度学习全景转3D
- [Adaptive O-CNN: A Patch-based Deep Representation of 3D Shapes](https://github.com/Microsoft/O-CNN),SIGGRAPH Asia 2018, **[[Project Page](https://wang-ps.github.io/AO-CNN.html)]**

## Other Collections

- [Matrix-Calculus](https://github.com/LynnHo/Matrix-Calculus), 矩阵求导方法
- [Mathematics](https://github.com/Ewenwan/Mathematics),数学知识点滴积累,矩阵,数值优化,神经网络反向传播,图优化,概率论,随机过程,卡尔曼滤波,粒子滤波,数学函数拟合

- [chinese-independent-blogs](https://github.com/timqian/chinese-independent-blogs), 中文独立博客集锦

- [StructureFlow: Image Inpainting via Structure-aware Appearance Flow](https://github.com/RenYurui/StructureFlow),图像inpainting

- [free-books](https://github.com/ruanyf/free-books),互联网上的免费书籍

- [AcademicPages](https://github.com/academicpages/academicpages.github.io),通用的学术主页模版

- [MMdnn](https://github.com/microsoft/MMdnn),实现深度学习模型之间的相互转换
- [tensorflow2caffemodel](https://github.com/abner2015/tensorflow2caffemodel),tensorflow模型转caffemodel
- [lihang-code](https://github.com/fengdu78/lihang-code),《统计学习方法》的代码实现
- [sse2neon](https://github.com/DLTcollab/sse2neon),[sse2neon](https://github.com/jratcliff63367/sse2neon),SSE转neon，嵌入式移植时可能会用到;
- [Production-Level-Deep-Learning](https://github.com/alirezadir/Production-Level-Deep-Learning),深度学习模型部署流程
- [动手学深度学习Dive-into-DL-PyTorch](https://github.com/ShusenTang/Dive-into-DL-PyTorch)
- [machine-learning-yearning-cn](https://github.com/deeplearning-ai/machine-learning-yearning-cn)，Machine Learning Yearning 中文版 - 《机器学习训练秘籍》 - Andrew Ng 著
- [academicpages.github.io](https://github.com/academicpages/academicpages.github.io)，学术主页模板
- [Coursera-ML-AndrewNg-Notes](https://github.com/fengdu78/Coursera-ML-AndrewNg-Notes),吴恩达老师的机器学习课程个人笔记
- [machine-learning-notes](https://github.com/roboticcam/machine-learning-notes),机器学习，概率模型和深度学习的讲义(1500+页)和视频链接
- [CNN-Visualization](https://github.com/scutan90/CNN-Visualization),CNN可视化、理解CNN
- [Awesome Semantic Segmentation](https://github.com/mrgloom/awesome-semantic-segmentation), 语义分割集合
- [IROS2018 SLAM Collections](https://github.com/mengyuest/iros2018-slam-papers), IROS 2018集合
- [VP-SLAM-SC-papers](https://github.com/TerenceCYJ/VP-SLAM-SC-papers),Visual Positioning & SLAM & Spatial Cognition 论文统计与分析
- [Awesome System for Machine Learning](https://github.com/HuaizhengZhang/Awesome-System-for-Machine-Learning)
- [Machine-Learning-With-Python](https://github.com/Thinkgamer/Machine-Learning-With-Python), 《机器学习实战》python代码实现
- [How to learn robotics](https://github.com/qqfly/how-to-learn-robotics), 开源机器人学学习指南
- [Awesome Deep Vision](https://github.com/kjw0612/awesome-deep-vision),DL在CV领域的应用
- [Single-Image-Super-Resolution](https://github.com/YapengTian/Single-Image-Super-Resolution), 一个有关**图像超分辨**的合集
- [ai report](https://github.com/wifity/ai-report), AI相关的研究报告
- [State-of-the-art papers and code](https://paperswithcode.com/sota),搜集了目前sota的论文以及代码
- [CVPR 2019 (Papers/Codes/Project/Paper reading)](https://github.com/extreme-assistant/cvpr2019)
- [A curated list of papers & resources linked to 3D reconstruction from images](https://github.com/openMVG/awesome_3DReconstruction_list),有关三维重建的论文汇总
- [SLAM-Jobs](https://github.com/nebula-beta/SLAM-Jobs), SLAM/SFM求职指南

- [Spatial Attentive Single-Image Deraining with a High Quality Real Rain Dataset](https://github.com/stevewongv/SPANet),CVPR 2019,去雨
- [Densely Connected Pyramid Dehazing Network](https://github.com/hezhangsprinter/DCPDN),CVPR 2018,去雾
- [MMSR](https://github.com/open-mmlab/mmsr)，MMLAB推出的超分辨工具箱
- [深度学习OCR](https://github.com/Bartzi/stn-ocr)
- [西瓜书🍉学习笔记](https://github.com/Vay-keen/Machine-learning-learning-notes)
- [awesome-reinforcement-learning-zh](https://github.com/wwxFromTju/awesome-reinforcement-learning-zh),强化学习从入门到放弃的资料

- [Deep Plug-and-Play Super-Resolution for Arbitrary Blur Kernels](https://github.com/cszn/DPSR),CVPR 2019,超分辨
- [Cool Fashion Papers](https://github.com/lzhbrian/Cool-Fashion-Papers), Cool resources about Fashion + AI.
- [Deep Flow-Guided Video Inpainting](https://github.com/nbei/Deep-Flow-Guided-Video-Inpainting),CVPR 2019, **[[Paper](https://arxiv.org/pdf/1806.10447.pdf)]** ,图像修复
- [YOLACT: Real-time Instance Segmentation](https://github.com/dbolya/yolact)
- [LPRNet: License Plate Recognition via Deep Neural Networks](https://github.com/lyl8213/Plate_Recognition-LPRnet), **[[Paper](https://arxiv.org/pdf/1806.10447.pdf)]** 
- [CHINESE-OCR](https://github.com/xiaofengShi/CHINESE-OCR), 运用tf实现自然场景文字检测
- [BeautyCamera](https://github.com/PerpetualSmile/BeautyCamera), 美颜相机，具有人脸检测、磨皮美白人脸、滤镜、调节图片、摄像功能
- [CV-arXiv-Daily](https://github.com/zhengzhugithub/CV-arXiv-Daily), 分享计算机视觉每天的arXiv文章
- [Pluralistic-Inpainting](https://github.com/lyndonzheng/Pluralistic-Inpainting), [ArXiv](https://arxiv.org/abs/1903.04227) | [Project Page](http://www.chuanxiaz.com/publication/pluralistic/) | [Online Demo](http://www.chuanxiaz.com/project/pluralistic/) | [Video(demo)](https://www.youtube.com/watch?v=9V7rNoLVmSs)
- [An Interactive Introduction to Fourier Transforms](https://github.com/Jezzamonn/fourier), 超棒的傅里叶变换图形化解释
- [pumpkin-book](https://github.com/datawhalechina/pumpkin-book), 《机器学习》（西瓜书）公式推导解析
- [Julia](https://github.com/JuliaLang/julia)
- [A Julia machine learning framework](https://github.com/alan-turing-institute/MLJ.jl)，一种基于Julia的机器学习框架
- [High-Performance Face Recognition Library on PyTorch](https://github.com/ZhaoJ9014/face.evoLVe.PyTorch)，人脸识别库
- [Deep-Learning-Coursera](https://github.com/enggen/Deep-Learning-Coursera)，深度学习教程（deeplearning.ai）
- [The best resources around Machine Learning](https://github.com/RemoteML/bestofml)
- [VGGFace2: A dataset for recognising faces across pose and age](https://github.com/cydonia999/VGGFace2-pytorch)
- [Statistical learning methods](https://github.com/SmirkCao/Lihang)，统计学习方法
- [End-to-end Adversarial Learning for Generative Conversational Agents](https://live.bilibili.com/7332534?visit_id=9ytrx9lpsy80)，2017，介绍了一种端到端的基于GAN的聊天机器人
- [Residual Non-local Attention Networks for Image Restoration](https://github.com/yulunzhang/RNAN),ICLR 2019.
- [MSGAN: Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis](https://github.com/HelenMao/MSGAN), CVPR 2019,**[[Paper](https://arxiv.org/abs/1903.05628)]**
- [SPADE: Semantic Image Synthesis with Spatially-Adaptive Normalization](https://github.com/NVlabs/SPADE),CVPR 2019, **[[Project Page](https://nvlabs.github.io/SPADE/)]**
- [Faceswap with Pytorch or DeepFake with Pytorch](https://github.com/Oldpan/Faceswap-Deepfake-Pytorch), 换脸
- [DeepFaceLab](https://github.com/iperov/DeepFaceLab), 换脸

## Contribute

❤ Please feel free to pull requests to add links.

## Sponsorship

[![Powered by DartNode](https://dartnode.com/branding/DN-Open-Source-sm.png)](https://dartnode.com "Powered by DartNode - Free VPS for Open Source")

## License

[![CC0](http://mirrors.creativecommons.org/presskit/buttons/88x31/svg/cc-zero.svg)](https://creativecommons.org/publicdomain/zero/1.0/)

## Star History

[![Star History Chart](https://api.star-history.com/svg?repos=Vincentqyw/Recent-Stars-2022&type=Date)](https://star-history.com/#Vincentqyw/Recent-Stars-2022&Date)

Recent-Stars-2025

Owner Repos

Recent-Stars-2025 Latest Version Download

# Use via CDN

Was this content helpful?

Recent Feedback

Recent-Stars-2025

Owner Repos

Recent-Stars-2025 Latest Version Download

# Use via CDN

Was this content helpful?

Recent Feedback

Download README