Uncertainty-Aware 4D Gaussian Splatting for Monocular Occluded Human Rendering
This addresses the challenge of rendering occluded humans in monocular videos, which is important for applications like virtual reality and animation, and represents an incremental improvement over prior methods.
The paper tackles the problem of high-fidelity rendering of dynamic humans from monocular videos under occlusions, achieving state-of-the-art rendering fidelity and robustness as demonstrated on ZJU-MoCap and OcMotion datasets.
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 Double 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 ZJU-MoCap and OcMotion demonstrate that U-4DGS achieves SOTA rendering fidelity and robustness.