Shuai Zhang, Zhanpeng Ouyang, Zhengqing Chen, Ruohong Mei, Shaoyu Chen, Weiqiang Ren, Hui Sun, Qian Zhang · 2026 · arXiv
DOI: 10.48550/arXiv.2610.28521 · open-access PDF
비디오 생성 및 3D 재구성은 일반적으로 별도의 표현을 사용하여 RGB 디코딩 및 시각적 재코딩을 필요로하여 생성 된 라틴트에서 기하학을 복구합니다. 우리는 비디오 생성 된 라틴트 공간과 기하학적 기능 공간을 연결하여 직접 비디오 라틴트에서 3D 기하학을 예측합니다. 우리는 Wan2.1 및 V-RAE를위한 표현 특정 브릿지를 개발하여 중간 RGB 경로없이 카메라, 깊이 및 3D 포인트 구름의 피드 예측을 허용합니다.
Machine translation (Meta M2M100); the English original follows.
Video generation and feed-forward 3D reconstruction typically use separate representations, requiring RGB decoding and visual re-encoding to recover geometry from generated latents. We propose Latent Bridge, which connects video generative latent spaces with geometric feature spaces to directly predict 3D geometry from video latents. We develop representation-specific bridges for Wan2.1 and V-RAE, enabling feed-forward prediction of cameras, depth, and 3D point clouds without the intermediate RGB pathway. Each bridge is trained on RGB videos through feature distillation, while the video encode
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=2610.28521, 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