RiGS decomposes scenes into static, rigid, and transient 4D Gaussians with an object-wise dynamic mask and scene flow guidance to model multi-scale motions and achieve SOTA novel view synthesis.
Fast dynamic radiance fields with time-aware neural voxels
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2verdicts
UNVERDICTED 2representative citing papers
4D Neural Voxel Splatting uses a compact neural voxel set with deformation fields instead of per-timestamp Gaussians to cut memory and speed training for dynamic scene rendering while keeping image quality.
citing papers explorer
-
RiGS: Rigid-aware 4D Gaussian Splatting from a Single Monocular Video
RiGS decomposes scenes into static, rigid, and transient 4D Gaussians with an object-wise dynamic mask and scene flow guidance to model multi-scale motions and achieve SOTA novel view synthesis.
-
4D Neural Voxel Splatting: Dynamic Scene Rendering with Voxelized Guassian Splatting
4D Neural Voxel Splatting uses a compact neural voxel set with deformation fields instead of per-timestamp Gaussians to cut memory and speed training for dynamic scene rendering while keeping image quality.