Shuzhou Yang, Lanqing Guo, Lingen Li, Weiqi Li, Zhao Zhong, Liefeng Bo, Jian Zhang · 2026 · arXiv
DOI: 10.48550/arXiv.2610.31641 · open-access PDF
Penghapusan dan suntikan objek video adalah operasi pengeditan reciprocal antara keadaan video yang hadir dan tidak hadir, namun mereka berbeda secara substansial dalam kesulitan pelatihan. Penghapusan dapat secara efektif bootstrapped dari video inpainting dan disesuaikan lebih lanjut untuk menghapus efek interaksi yang terkait dengan objek. Namun, suntikan membutuhkan pengawasan berpasangan skala besar untuk memodelkan tampilan objek, dinamika, dan efek bergantung pada adegan, sementara pasangan dunia nyata yang disesuaikan dengan sempurna sulit untuk dikumpulkan dan data sintetis tidak memiliki realisme dan keragaman yang cukup.
Machine translation (Meta M2M100); the English original follows.
Video object removal and injection are reciprocal editing operations between object-present and object-absent video states, yet they differ substantially in training difficulty. Removal can be effectively bootstrapped from video inpainting and further adapted to erase object-related interaction effects. Injection, however, requires large-scale paired supervision to model object appearance, dynamics, and scene-dependent effects, while perfectly aligned real-world pairs are difficult to collect and synthetic data lacks sufficient realism and diversity. To address this challenge, we present UniVO
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.31641, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange