GRVS: a Generalizable and Recurrent Approach to Monocular Dynamic View Synthesis
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911557906071552 |
|---|---|
| author | Tanay, Thomas Brahimi, Mohammed Nazarczuk, Michal Zhang, Qingwen Catley-Chandar, Sibi Moreau, Arthur Zhang, Zhensong Pérez-Pellitero, Eduardo |
| author_facet | Tanay, Thomas Brahimi, Mohammed Nazarczuk, Michal Zhang, Qingwen Catley-Chandar, Sibi Moreau, Arthur Zhang, Zhensong Pérez-Pellitero, Eduardo |
| contents | Synthesizing novel views from monocular videos of dynamic scenes remains a challenging problem. Scene-specific methods that optimize 4D representations with explicit motion priors often break down in highly dynamic regions where multi-view information is hard to exploit. Diffusion-based approaches that integrate camera control into large pre-trained models can produce visually plausible videos but frequently suffer from geometric inconsistencies across both static and dynamic areas. Both families of methods also require substantial computational resources. Building on the success of generalizable models for static novel view synthesis, we adapt the framework to dynamic inputs and propose a new model with two key components: (1) a recurrent loop that enables unbounded and asynchronous mapping between input and target videos and (2) an efficient use of plane sweeps over dynamic inputs to disentangle camera and scene motion, and achieve fine-grained, six-degrees-of-freedom camera controls. We train and evaluate our model on the UCSD dataset and on Kubric-4D-dyn, a new monocular dynamic dataset featuring longer, higher resolution sequences with more complex scene dynamics than existing alternatives. Our model outperforms four Gaussian Splatting-based scene-specific approaches, as well as two diffusion-based approaches in reconstructing fine-grained geometric details across both static and dynamic regions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_29734 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | GRVS: a Generalizable and Recurrent Approach to Monocular Dynamic View Synthesis Tanay, Thomas Brahimi, Mohammed Nazarczuk, Michal Zhang, Qingwen Catley-Chandar, Sibi Moreau, Arthur Zhang, Zhensong Pérez-Pellitero, Eduardo Computer Vision and Pattern Recognition Synthesizing novel views from monocular videos of dynamic scenes remains a challenging problem. Scene-specific methods that optimize 4D representations with explicit motion priors often break down in highly dynamic regions where multi-view information is hard to exploit. Diffusion-based approaches that integrate camera control into large pre-trained models can produce visually plausible videos but frequently suffer from geometric inconsistencies across both static and dynamic areas. Both families of methods also require substantial computational resources. Building on the success of generalizable models for static novel view synthesis, we adapt the framework to dynamic inputs and propose a new model with two key components: (1) a recurrent loop that enables unbounded and asynchronous mapping between input and target videos and (2) an efficient use of plane sweeps over dynamic inputs to disentangle camera and scene motion, and achieve fine-grained, six-degrees-of-freedom camera controls. We train and evaluate our model on the UCSD dataset and on Kubric-4D-dyn, a new monocular dynamic dataset featuring longer, higher resolution sequences with more complex scene dynamics than existing alternatives. Our model outperforms four Gaussian Splatting-based scene-specific approaches, as well as two diffusion-based approaches in reconstructing fine-grained geometric details across both static and dynamic regions. |
| title | GRVS: a Generalizable and Recurrent Approach to Monocular Dynamic View Synthesis |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.29734 |