CoMatcher

KO | EN

gitlite — search

#javascript #react #llm #machine-learning #rust #linux #docker #nodejs #windows #awesome-list #security #mcp #openai #open-source

(★ 23)

[CVPR'25] CoMatcher: Multi-View Collaborative Feature Matching

CoMatcher Latest Version Download

Download Latest Version (.zip)

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# [CVPR'25] CoMatcher: Multi-View Collaborative Feature Matching

[[`Paper`](https://arxiv.org/pdf/2504.01872)]

## Abstract
This paper proposes a multi-view collaborative matching strategy for reliable track construction in complex scenarios.
We observe that the pairwise matching paradigms applied to image set matching often result in ambiguous estimation when the selected independent pairs exhibit significant occlusions or extreme viewpoint changes.
This challenge primarily stems from the inherent uncertainty in interpreting intricate 3D structures based on limited two-view observations, as the 3D-to-2D projection leads to significant information loss.
To address this, we introduce CoMatcher, a deep multi-view matcher to (i) leverage complementary context cues from different views to form a holistic 3D scene understanding and (ii) utilize cross-view projection consistency to infer a reliable global solution.
Building on CoMatcher, we develop a groupwise framework that fully exploits cross-view relationships for large-scale matching tasks.
Extensive experiments on various complex scenarios demonstrate the superiority of our method over the mainstream two-view matching paradigm.

## Installation
```bash
git clone https://github.com/EATMustard/CoMatcher.git
cd comatcher
conda env create -f environment.yml
```

## Evaluation

### HPatches
When running the evaluation script, the dataset will be automatically downloaded to the data directory by default.
We provide two evaluation scripts: one for pairwise matching and one for single-forward multi-view matching.
```bash
python -m src.eval.multiview_hpatches --conf superpoint+comatcher --overwrite  # for comatcher
python -m src.eval.hpatches --conf superpoint+lightglue --overwrite            # for pairwise methods like superpoint+lightglue
```
Additionally, for homography estimation, if you wish to use Poselib instead of OpenCV’s estimator, use the following command (refer to glue-factory for more details):
```bash
python -m src.eval.multiview_hpatches --conf superpoint+comatcher --overwrite \ 
  eval.estimator=poselib eval.ransac_th=-1
```

### MegaDepth
Since the original MegaDepth-1500 dataset is designed for two-view matching, we have recaptured multi-view images from its scenes for evaluation.
This forms a “3-to-1” quadruple dataset: Multi-View MegaDepth-1500, which contains 4500 image pairs.
We also provide two evaluation scripts for both approaches:
```bash
python -m src.eval.multiview_megadepth1500 --conf superpoint+comatcher --overwrite
```

If you want to eval two-view matches in the same dataset(4500 pairs), like SuperPoint+LightGlue model:
```bash
python -m src.eval.multiview_megadepth1500 --conf superpoint+comatcher --overwrite
python -m src.eval.megadepth4500 --conf superpoint+lightglue-official --overwrite
```

## Training

CoMatcher follows a two-step training strategy: pre-training on a synthetic dataset, followed by fine-tuning on MegaDepth.
```bash
python -m src.train sp+comatcher_homography \  # experiment name
--conf src/configs/multi-view/superpoint+comatcher_homography.yaml

python -m src.train sp+comatcher_megadepth \
--conf src/configs/multi-view/superpoint+comatcher_megadepth.yaml \
train.load_experiment=sp+comatcher_homography
```

To evaluate a trained model, use the `--checkpoint` argument:
```bash
python -m src.eval.multiview_megadepth1500 --checkpoint sp+comatcher
```

## Comming soon

- [x] End-to-end track construction toolkit embedded in COLMAP
- [x] Pretrained checkpoints
- [x] IMC evaluations
- [x] More baselines

## Acknowledgements
We extend our gratitude to the developers of the `Glue-Factory` codebase for their excellent work, which enabled us to extend their framework to multi-view scenarios.

## Citation
```bibtex
@inproceedings{zhang2025comatcher,
  title     = {CoMatcher: Multi-View Collaborative Feature Matching},
  author    = {Zhang, Jintao and Xia, Zimin and Dong, Mingyue and Shen, Shuhan and Yue, Linwei and Zheng, Xianwei},
  booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference},
  pages     = {21970--21980},
  year      = {2025}
}
```

CoMatcher

CoMatcher Latest Version Download

Today's picks

Was this content helpful?

Recent Feedback

CoMatcher

CoMatcher Latest Version Download

Today's picks

Was this content helpful?

Recent Feedback

Download README