Uncertainty-Aware 4D Gaussian Splatting for Monocular Occluded Human Rendering

TL;DR

This paper introduces U-4DGS, a probabilistic framework for monocular human rendering that effectively manages occlusions by modeling uncertainty and applying confidence-aware regularizations.

Contribution

It presents a novel probabilistic approach with uncertainty maps and regularizations to improve occluded human rendering from monocular videos.

Findings

Achieves state-of-the-art fidelity on ZJU-MoCap and OcMotion datasets.

Effectively attenuates artifacts caused by unreliable observations.

Maintains geometric consistency in occluded regions.

Abstract

High-fidelity rendering of dynamic humans from monocular videos typically degrades catastrophically under occlusions. Existing solutions incorporate external priors-either hallucinating missing content via generative models, which induces severe temporal flickering, or imposing rigid geometric heuristics that fail to capture diverse appearances. To this end, we reformulate the task as a Maximum A Posteriori estimation problem under heteroscedastic observation noise. In this paper, we propose U-4DGS, a framework integrating a Probabilistic Deformation Network and a Joint Rasterization pipeline. This architecture renders pixel-aligned uncertainty maps that act as an adaptive gradient modulator, automatically attenuating artifacts from unreliable observations. Furthermore, to prevent geometric drift in regions lacking reliable visual cues, we enforce Confidence-Aware Regularizations, which leverage the learned uncertainty to selectively propagate spatial-temporal validity. Extensive experiments on the ZJU-MoCap and OcMotion datasets demonstrate that U-4DGS achieves state-of-the-art rendering fidelity and robustness.