Physics-Aware Human-Object Rendering from Sparse Views via 3D Gaussian Splatting
This addresses the challenge of generating physically plausible human-object interactions for applications like virtual reality or robotics, but it is incremental as it builds on existing 3D Gaussian Splatting techniques.
The paper tackles the problem of rendering realistic human-object interactions from sparse-view inputs, achieving superior rendering quality, efficiency, and physical plausibility compared to existing methods on the HODome dataset.
Rendering realistic human-object interactions (HOIs) from sparse-view inputs is challenging due to occlusions and incomplete observations, yet crucial for various real-world applications. Existing methods always struggle with either low rendering qualities (\eg, visual fidelity and physically plausible HOIs) or high computational costs. To address these limitations, we propose HOGS (Human-Object Rendering via 3D Gaussian Splatting), a novel framework for efficient and physically plausible HOI rendering from sparse views. Specifically, HOGS combines 3D Gaussian Splatting with a physics-aware optimization process. It incorporates a Human Pose Refinement module for accurate pose estimation and a Sparse-View Human-Object Contact Prediction module for efficient contact region identification. This combination enables coherent joint rendering of human and object Gaussians while enforcing physically plausible interactions. Extensive experiments on the HODome dataset demonstrate that HOGS achieves superior rendering quality, efficiency, and physical plausibility compared to existing methods. We further show its extensibility to hand-object grasp rendering tasks, presenting its broader applicability to articulated object interactions.