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

arXiv: https://arxiv.org/abs/2608.05565 · HTML: https://mlsanity.com/paper/2608.05565/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 35 references that are in the map.
- First posted on arXiv 6 Aug 2026.

## Builds on (most cited first, 22 of 22)

- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024)
- [GLM-5: from Vibe Coding to Agentic Engineering](https://mlsanity.com/paper/2602.15763/) (2026)
- [VACE: All-in-One Video Creation and Editing](https://mlsanity.com/paper/2503.07598/) (2025)
- [PhysDreamer: Physics-Based Interaction with 3D Objects via Video Generation](https://mlsanity.com/paper/2404.13026/) (2024)
- [Learning Joint Spatial-Temporal Transformations for Video Inpainting](https://mlsanity.com/paper/2007.10247/) (2020)
- [FuseFormer: Fusing Fine-Grained Information in Transformers for Video Inpainting](https://mlsanity.com/paper/2109.02974/) (2021)
- [DiffuEraser: A Diffusion Model for Video Inpainting](https://mlsanity.com/paper/2501.10018/) (2025)
- [RealCam-I2V: Real-World Image-to-Video Generation with Interactive Complex Camera Control](https://mlsanity.com/paper/2502.10059/) (2025)
- [DreamPhysics: Learning Physics-Based 3D Dynamics with Video Diffusion Priors](https://mlsanity.com/paper/2406.01476/) (2024)
- [ROSE: Remove Objects with Side Effects in Videos](https://mlsanity.com/paper/2508.18633/) (2025)
- [Kiwi-Edit: Versatile Video Editing via Instruction and Reference Guidance](https://mlsanity.com/paper/2603.02175/) (2026)
- [Omni-Effects: Unified and Spatially-Controllable Visual Effects Generation](https://mlsanity.com/paper/2508.07981/) (2025)
- [VIVA: VLM-Guided Instruction-Based Video Editing with Reward Optimization](https://mlsanity.com/paper/2512.16906/) (2025)
- [EffectErase: Joint Video Object Removal and Insertion for High-Quality Effect Erasing](https://mlsanity.com/paper/2603.19224/) (2026)
- [VORNet: Spatio-temporally Consistent Video Inpainting for Object Removal](https://mlsanity.com/paper/1904.06726/) (2019)
- [VOID: Video Object and Interaction Deletion](https://mlsanity.com/paper/2604.02296/) (2026)
- [Object-WIPER : Training-Free Object and Associated Effect Removal in Videos](https://mlsanity.com/paper/2601.06391/) (2026)
- [From Ideal to Real: Stable Video Object Removal under Imperfect Conditions](https://mlsanity.com/paper/2603.09283/) (2026)
- [MoZoo:Unleashing Video Diffusion power in animal fur and muscle simulation](https://mlsanity.com/paper/2605.13857/) (2026)
- [DualEraser: Joint Video Object and Effect Removal via Balanced Text-Mask Guidance and Decoupled Locator-Preserver](https://mlsanity.com/paper/2605.30045/) (2026)

## Abstract (arXiv)

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.