G-Skin: Learning to Bind 3D Gaussians with Generative Visual Priors

2026-08-03

AI Summary

Existing methods struggle to achieve effective skinning animation for arbitrary skeleton topologies due to the scarcity of high-quality 3D Gaussian binding data. This work proposes G-Skin, a novel framework that introduces generative 2D visual priors into this task for the first time. By leveraging pose-controllable image generation to obtain motion-based pseudo-supervision and incorporating geometry-aware regularization, G-Skin optimizes skinning weights for 3D Gaussian representations without requiring ground-truth 3D binding data. The approach supports various enhanced 3D Gaussian representations and significantly improves animation fidelity and structural consistency. Extensive experiments demonstrate that G-Skin outperforms existing methods across multiple scenarios and effectively suppresses rendering artifacts induced by articulated motion.

Abstract

3D Gaussian Splatting has achieved remarkable success in photorealistic and efficient rendering, leading to a rapid increase in 3D assets represented by 3D Gaussian primitives. Directly rigging these assets with arbitrary skeleton topologies is highly desirable. However, training a feed-forward skinning framework is infeasible due to the lack of high-quality 3D Gaussian rigging datasets. An alternative solution is to transfer mesh-based techniques to 3D Gaussian-based representation, but 3D Gaussian primitives are not restricted to the surface and lack explicit topological connectivity. Moreover, this kind of method suffers from poor generalization to unseen data due to its strong dependence on training data, while acquiring high-quality rigging data is prohibitively expensive. To address this challenging problem, we propose G-Skin, a novel generative skinning framework designed for expressive and high-fidelity animation with 3D Gaussian representation. To overcome this 3D data scarcity, we introduce a skeleton-controllable image generation model leveraging 2D vision foundation models to distill powerful motion priors into pseudo-guidance. Guided by these priors, we formulate an optimization pipeline incorporating geometry-aware regularizations, which stabilizes the learning process and ensures smooth, structurally coherent skinning weights. G-Skin also generalizes flexibly to the augmented variants of 3D Gaussian representation designed to mitigate animation-induced rendering artifacts. Extensive experiments validate the effectiveness of our approach, demonstrating clear advantages over state-of-the-art methods. Project page: https://yaoyx689.github.io/GSkin.html.

Problem

• 3D Gaussian Splatting
• skinning
• rigging
• animation
• generative priors

Innovation

• 3D Gaussian Splatting
• generative skinning
• motion priors
• geometry-aware regularization
• skeleton-controllable generation