GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910859783045120 |
|---|---|
| author | Ren, Xuanchi Shen, Tianchang Huang, Jiahui Ling, Huan Lu, Yifan Nimier-David, Merlin Müller, Thomas Keller, Alexander Fidler, Sanja Gao, Jun |
| author_facet | Ren, Xuanchi Shen, Tianchang Huang, Jiahui Ling, Huan Lu, Yifan Nimier-David, Merlin Müller, Thomas Keller, Alexander Fidler, Sanja Gao, Jun |
| contents | We present GEN3C, a generative video model with precise Camera Control and temporal 3D Consistency. Prior video models already generate realistic videos, but they tend to leverage little 3D information, leading to inconsistencies, such as objects popping in and out of existence. Camera control, if implemented at all, is imprecise, because camera parameters are mere inputs to the neural network which must then infer how the video depends on the camera. In contrast, GEN3C is guided by a 3D cache: point clouds obtained by predicting the pixel-wise depth of seed images or previously generated frames. When generating the next frames, GEN3C is conditioned on the 2D renderings of the 3D cache with the new camera trajectory provided by the user. Crucially, this means that GEN3C neither has to remember what it previously generated nor does it have to infer the image structure from the camera pose. The model, instead, can focus all its generative power on previously unobserved regions, as well as advancing the scene state to the next frame. Our results demonstrate more precise camera control than prior work, as well as state-of-the-art results in sparse-view novel view synthesis, even in challenging settings such as driving scenes and monocular dynamic video. Results are best viewed in videos. Check out our webpage! https://research.nvidia.com/labs/toronto-ai/GEN3C/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_03751 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control Ren, Xuanchi Shen, Tianchang Huang, Jiahui Ling, Huan Lu, Yifan Nimier-David, Merlin Müller, Thomas Keller, Alexander Fidler, Sanja Gao, Jun Computer Vision and Pattern Recognition Graphics We present GEN3C, a generative video model with precise Camera Control and temporal 3D Consistency. Prior video models already generate realistic videos, but they tend to leverage little 3D information, leading to inconsistencies, such as objects popping in and out of existence. Camera control, if implemented at all, is imprecise, because camera parameters are mere inputs to the neural network which must then infer how the video depends on the camera. In contrast, GEN3C is guided by a 3D cache: point clouds obtained by predicting the pixel-wise depth of seed images or previously generated frames. When generating the next frames, GEN3C is conditioned on the 2D renderings of the 3D cache with the new camera trajectory provided by the user. Crucially, this means that GEN3C neither has to remember what it previously generated nor does it have to infer the image structure from the camera pose. The model, instead, can focus all its generative power on previously unobserved regions, as well as advancing the scene state to the next frame. Our results demonstrate more precise camera control than prior work, as well as state-of-the-art results in sparse-view novel view synthesis, even in challenging settings such as driving scenes and monocular dynamic video. Results are best viewed in videos. Check out our webpage! https://research.nvidia.com/labs/toronto-ai/GEN3C/ |
| title | GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control |
| topic | Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2503.03751 |