Interaction-Aware 4D Gaussian Splatting for Dynamic Hand-Object Interaction Reconstruction
By: Hao Tian , Chenyangguang Zhang , Rui Liu and more
Potential Business Impact:
Makes 3D models of hands and objects interact.
This paper focuses on a challenging setting of simultaneously modeling geometry and appearance of hand-object interaction scenes without any object priors. We follow the trend of dynamic 3D Gaussian Splatting based methods, and address several significant challenges. To model complex hand-object interaction with mutual occlusion and edge blur, we present interaction-aware hand-object Gaussians with newly introduced optimizable parameters aiming to adopt piecewise linear hypothesis for clearer structural representation. Moreover, considering the complementarity and tightness of hand shape and object shape during interaction dynamics, we incorporate hand information into object deformation field, constructing interaction-aware dynamic fields to model flexible motions. To further address difficulties in the optimization process, we propose a progressive strategy that handles dynamic regions and static background step by step. Correspondingly, explicit regularizations are designed to stabilize the hand-object representations for smooth motion transition, physical interaction reality, and coherent lighting. Experiments show that our approach surpasses existing dynamic 3D-GS-based methods and achieves state-of-the-art performance in reconstructing dynamic hand-object interaction.
Similar Papers
RobustSplat++: Decoupling Densification, Dynamics, and Illumination for In-the-Wild 3DGS
CV and Pattern Recognition
Makes 3D pictures ignore moving things and changing light.
AHA! Animating Human Avatars in Diverse Scenes with Gaussian Splatting
CV and Pattern Recognition
Makes animated people look real in 3D videos.
Follow My Hold: Hand-Object Interaction Reconstruction through Geometric Guidance
CV and Pattern Recognition
Makes 3D object shapes from one picture.