U-4DGS reformulates occluded dynamic human rendering as MAP estimation under heteroscedastic noise, using a Probabilistic Deformation Network and uncertainty-modulated joint rasterization plus confidence-aware regularizations to deliver SOTA fidelity and robustness on ZJU-MoCap and OcMotion.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
MoPO uses a motion de-occlusion module and motion-aware fusion to complete occluded joints via pose prediction and refine human mesh recovery, claiming state-of-the-art results on occlusion and standard benchmarks.
citing papers explorer
-
Uncertainty-Aware 4D Gaussian Splatting for Monocular Occluded Human Rendering
U-4DGS reformulates occluded dynamic human rendering as MAP estimation under heteroscedastic noise, using a Probabilistic Deformation Network and uncertainty-modulated joint rasterization plus confidence-aware regularizations to deliver SOTA fidelity and robustness on ZJU-MoCap and OcMotion.
-
MoPO: Incorporating Motion Prior for Occluded Human Mesh Recovery
MoPO uses a motion de-occlusion module and motion-aware fusion to complete occluded joints via pose prediction and refine human mesh recovery, claiming state-of-the-art results on occlusion and standard benchmarks.