Salvato in:
| Autori principali: | , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2403.17920 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916438404497408 |
|---|---|
| author | Bahmani, Sherwin Liu, Xian Yifan, Wang Skorokhodov, Ivan Rong, Victor Liu, Ziwei Liu, Xihui Park, Jeong Joon Tulyakov, Sergey Wetzstein, Gordon Tagliasacchi, Andrea Lindell, David B. |
| author_facet | Bahmani, Sherwin Liu, Xian Yifan, Wang Skorokhodov, Ivan Rong, Victor Liu, Ziwei Liu, Xihui Park, Jeong Joon Tulyakov, Sergey Wetzstein, Gordon Tagliasacchi, Andrea Lindell, David B. |
| contents | Recent techniques for text-to-4D generation synthesize dynamic 3D scenes using supervision from pre-trained text-to-video models. However, existing representations for motion, such as deformation models or time-dependent neural representations, are limited in the amount of motion they can generate-they cannot synthesize motion extending far beyond the bounding box used for volume rendering. The lack of a more flexible motion model contributes to the gap in realism between 4D generation methods and recent, near-photorealistic video generation models. Here, we propose TC4D: trajectory-conditioned text-to-4D generation, which factors motion into global and local components. We represent the global motion of a scene's bounding box using rigid transformation along a trajectory parameterized by a spline. We learn local deformations that conform to the global trajectory using supervision from a text-to-video model. Our approach enables the synthesis of scenes animated along arbitrary trajectories, compositional scene generation, and significant improvements to the realism and amount of generated motion, which we evaluate qualitatively and through a user study. Video results can be viewed on our website: https://sherwinbahmani.github.io/tc4d. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_17920 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | TC4D: Trajectory-Conditioned Text-to-4D Generation Bahmani, Sherwin Liu, Xian Yifan, Wang Skorokhodov, Ivan Rong, Victor Liu, Ziwei Liu, Xihui Park, Jeong Joon Tulyakov, Sergey Wetzstein, Gordon Tagliasacchi, Andrea Lindell, David B. Computer Vision and Pattern Recognition Recent techniques for text-to-4D generation synthesize dynamic 3D scenes using supervision from pre-trained text-to-video models. However, existing representations for motion, such as deformation models or time-dependent neural representations, are limited in the amount of motion they can generate-they cannot synthesize motion extending far beyond the bounding box used for volume rendering. The lack of a more flexible motion model contributes to the gap in realism between 4D generation methods and recent, near-photorealistic video generation models. Here, we propose TC4D: trajectory-conditioned text-to-4D generation, which factors motion into global and local components. We represent the global motion of a scene's bounding box using rigid transformation along a trajectory parameterized by a spline. We learn local deformations that conform to the global trajectory using supervision from a text-to-video model. Our approach enables the synthesis of scenes animated along arbitrary trajectories, compositional scene generation, and significant improvements to the realism and amount of generated motion, which we evaluate qualitatively and through a user study. Video results can be viewed on our website: https://sherwinbahmani.github.io/tc4d. |
| title | TC4D: Trajectory-Conditioned Text-to-4D Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.17920 |