MoCam unifies static and dynamic novel view synthesis by temporally decoupling geometric alignment and appearance refinement within the diffusion denoising process.
In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2representative citing papers
citing papers explorer
-
MoCam: Unified Novel View Synthesis via Structured Denoising Dynamics
MoCam unifies static and dynamic novel view synthesis by temporally decoupling geometric alignment and appearance refinement within the diffusion denoising process.
- DF3DV-1K: A Large-Scale Dataset and Benchmark for Distractor-Free Novel View Synthesis