MoCam: Unified Novel View Synthesis via Structured Denoising Dynamics
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910213615910912 |
|---|---|
| author | Liu, Haofeng Zhou, Yang Wang, Ziheng Xu, Zhengbo Peng, Zhan Ma, Jie Liang, Jun He, Shengfeng Li, Jing |
| author_facet | Liu, Haofeng Zhou, Yang Wang, Ziheng Xu, Zhengbo Peng, Zhan Ma, Jie Liang, Jun He, Shengfeng Li, Jing |
| contents | Generative novel view synthesis faces a fundamental dilemma: geometric priors provide spatial alignment but become sparse and inaccurate under view changes, while appearance priors offer visual fidelity but lack geometric correspondence. Existing methods either propagate geometric errors throughout generation or suffer from signal conflicts when fusing both statically. We introduce MoCam, which employs structured denoising dynamics to orchestrate a coordinated progression from geometry to appearance within the diffusion process. MoCam first leverages geometric priors in early stages to anchor coarse structures and tolerate their incompleteness, then switches to appearance priors in later stages to actively correct geometric errors and refine details. This design naturally unifies static and dynamic view synthesis by temporally decoupling geometric alignment and appearance refinement within the diffusion process. Experiments demonstrate that MoCam significantly outperforms prior methods, particularly when point clouds contain severe holes or distortions, achieving robust geometry-appearance disentanglement. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_12119 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MoCam: Unified Novel View Synthesis via Structured Denoising Dynamics Liu, Haofeng Zhou, Yang Wang, Ziheng Xu, Zhengbo Peng, Zhan Ma, Jie Liang, Jun He, Shengfeng Li, Jing Computer Vision and Pattern Recognition Graphics Generative novel view synthesis faces a fundamental dilemma: geometric priors provide spatial alignment but become sparse and inaccurate under view changes, while appearance priors offer visual fidelity but lack geometric correspondence. Existing methods either propagate geometric errors throughout generation or suffer from signal conflicts when fusing both statically. We introduce MoCam, which employs structured denoising dynamics to orchestrate a coordinated progression from geometry to appearance within the diffusion process. MoCam first leverages geometric priors in early stages to anchor coarse structures and tolerate their incompleteness, then switches to appearance priors in later stages to actively correct geometric errors and refine details. This design naturally unifies static and dynamic view synthesis by temporally decoupling geometric alignment and appearance refinement within the diffusion process. Experiments demonstrate that MoCam significantly outperforms prior methods, particularly when point clouds contain severe holes or distortions, achieving robust geometry-appearance disentanglement. |
| title | MoCam: Unified Novel View Synthesis via Structured Denoising Dynamics |
| topic | Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2605.12119 |