Henglei Lv, Bailin Deng, Xiaoqiang Liu, Yichen Wang, Haoxian Zhang, Pengfei Wan, Lin Gao · 2026 · arXiv
DOI: 10.48550/arXiv.2610.29780 · open-access PDF
Memahami dan memodelkan transportasi cahaya dalam adegan yang berpusat pada manusia adalah tantangan yang lama. Sementara kemajuan baru-baru ini dalam model diffusi telah mendorong penelitian dalam relighting, kontrol pencahayaan yang akurat masih tertunda, terutama karena kekurangan beragam, kualitas tinggi, set data relighting video yang ditandai dengan tepat. Pendekatan relighting end-to-end yang ada memodelkan transportasi cahaya secara implisit melalui jaringan saraf, yang secara substansial mempersulit kontrol. Sebaliknya, beberapa karya menggunakan petunjuk iradiasi yang dilacak sebagai blueprint eksplisit untuk transportasi cahaya.
Machine translation (Meta M2M100); the English original follows.
Understanding and modeling light transport in human-centric scenes is a longstanding challenge. While recent progress in diffusion models has boosted research in relighting, precise illumination control still lags, primarily due to the scarcity of diverse, high-quality, precisely labeled video relighting datasets. Existing end-to-end relighting approaches model light transport implicitly through neural networks, which substantially complicates controllability. In contrast, some works resort to path-traced irradiance cues as an explicit blueprint for light transport. However, such constructed i
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=2610.29780, 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