Metraipolis › archive › dc_152855ea0fa6

EffectLearner: World-Aware Object-Effect Reasoning for Real-World Video Object Removal — arXiv:2608.05565

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.05565
License (as archived)
CC0-1.0
Archived
2026-10-31T10:35:59.303Z
SHA-256 of the archived text
33aa3de480e3572e6a499ff696e6dabcf0cfc7897c3621ebffbfb8e08408a181
Stable URL of this page
https://metraipolis.com/documento/dc_152855ea0fa6

How to cite

EffectLearner: World-Aware Object-Effect Reasoning for Real-World Video Object Removal — arXiv:2608.05565 — arXiv (en), https://arxiv.org/abs/2608.05565 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_152855ea0fa6 (Metraipolis archive dc_152855ea0fa6, sha256 33aa3de480e3572e6a499ff696e6dabcf0cfc7897c3621ebffbfb8e08408a181)
BibTeX
@misc{dc152855ea0fa6,
  title = {EffectLearner: World-Aware Object-Effect Reasoning for Real-World Video Object Removal — arXiv:2608.05565},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.05565},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_152855ea0fa6; sha256 33aa3de480e3572e6a499ff696e6dabcf0cfc7897c3621ebffbfb8e08408a181},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.05565. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-07 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.05565 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-31T10:23:30.982Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).