EffectLearner-Official

KO | EN

gitlite — search

#ai-agents #self-hosted #sql #cloud-native #generative-ai #android #llm #javascript #video #nextjs

EffectLearner-Official

(★ 9)

EffectLearner: World-Aware Object-Effect Reasoning for Real-World Video Object Removal

File Explorer

ZIP Download

README.md

# 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

Link

Example

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

Official repository for **EffectLearner: World-Aware Object-Effect Reasoning for Real-World Video Object Removal**

[![arXiv](https://img.shields.io/badge/arXiv-2608.05565-b31b1b.svg)](https://arxiv.org/abs/2608.05565)
[![Project Page](https://img.shields.io/badge/Project‑Page-blue)](https://morleyolsen.github.io/EffectLearner/)
[![HuggingFace Dataset](https://img.shields.io/badge/%F0%9F%A4%97-Dataset-yellow)](https://huggingface.co/datasets/jenniferwuuu/EffectWorld)

## Overview
This is the official code repository for our paper *EffectLearner: World-Aware Object-Effect Reasoning for Real-World Video Object Removal*.

## Abstract
Video object removal must eliminate not only the target object but also its induced effects while maintaining high-fidelity and spatiotemporally coherent restoration. Existing methods mainly learn object-effect correspondences implicitly from predefined effect categories and fixed data distributions, limiting their generalization to complex real-world scenes involving compositional effects, spatially detached or weakly correlated effects, long-tail physical phenomena, and dynamically evolving interactions. We propose EffectLearner, a semantic-reasoning-enhanced framework that combines a VLM-based Object-Effect Reasoner with a DiT-based Video Eraser. Guided by a structured effect-analysis prompt, the Reasoner performs cross-modal reasoning over a target-highlighted video and extracts compact effect-aware context, which guides the Video Eraser toward comprehensive object-effect removal. Motion-aware mask guidance and motion-consistency supervision further improve removal coverage and spatiotemporal stability under object motion and evolving scene dynamics. To fully exploit the framework in challenging real-world scenarios, we further construct EffectWorld, a paired video dataset specifically designed for complex object-induced effects, and introduce a progressive training curriculum that combines common supervision with complex-effect data. On the standard ROSE-Bench, EffectLearner outperforms existing baselines on most metrics and achieves clear advantages on both EffectWorld-Eval and the challenging EffectWorld-Wild, demonstrating its ability to deliver high-quality video object removal in complex real-world scenes.

## Status
⌛️ Code Release Update: The training / inference code, model checkpoints and evaluation scripts are currently being organized and will be released as soon as possible.

- ✅ Paper: Released on [ARXIV](https://arxiv.org/abs/2608.05565)
- ✅ Project page: Released [HERE](https://morleyolsen.github.io/EffectLearner/)
- ✅ EffectWorld dataset: Released on [Hugging Face](https://huggingface.co/datasets/jenniferwuuu/EffectWorld) 🤗
- ⏳ Model weights: Coming soon
- ⏳ Training & inference codes: Coming soon

## Citation
If you find our work useful, please cite our paper:
```bibtex
@misc{wu2026effectlearnerworldawareobjecteffectreasoning,
      title={EffectLearner: World-Aware Object-Effect Reasoning for Real-World Video Object Removal}, 
      author={Feier Wu and Wanke Xia and Xu He and Zilang Zhou and Si Chen and Dongxia Liu and Liyang Chen and Qimeng Wu and Zhengbo Zhang and Wenming Yang and Zhiyong Wu},
      year={2026},
      eprint={2608.05565},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2608.05565}, 
}

EffectLearner-Official

File Explorer

# Use via CDN

Was this content helpful?

Recent Feedback

Download README