A generative video model conditioned on pixel-aligned 3D renderings produces consistent dynamic 3D Gaussian splats from monocular video and sets new SOTA in 4D reconstruction.
Vidar: Video diffusion-aware 4d reconstruction from monocular inputs.arXiv preprint arXiv:2506.18792, 2025
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
World from Motion: Generative Dynamic Gaussian Reconstruction from Monocular Video
A generative video model conditioned on pixel-aligned 3D renderings produces consistent dynamic 3D Gaussian splats from monocular video and sets new SOTA in 4D reconstruction.