发表机构
City University of Hong Kong; Central Media Technology Institute, Huawei; Central South University（香港城市大学; 华为中央媒体技术研究院; 中南大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文针对3D高斯资产绑定的难题，提出生成式蒙皮框架G-Skin，利用2D视觉基础模型提炼运动先验构建优化流程，可灵活泛化并优于现有方法。
AI 中文摘要
3D Gaussian Splatting在 photorealistic 和高效渲染方面取得了显著成功，催生了大量以3D高斯基元表示的3D资产。人们迫切希望为这些资产绑定任意骨架拓扑，但由于缺乏高质量的3D高斯绑定数据集，训练前馈蒙皮框架不可行。另一种解决方案是将基于网格的技术迁移到3D高斯表示，但3D高斯基元不受限于表面且缺乏显式拓扑连接性，且这类方法因高度依赖训练数据而对未见数据泛化性差，同时获取高质量绑定数据成本过高。为解决这一难题，本文提出G-Skin，一种专为3D高斯表示的高表现力高保真动画设计的新型生成式蒙皮框架。为克服3D数据稀缺问题，本文引入骨架可控图像生成模型，利用2D视觉基础模型将强大的运动先验提炼为伪引导。在这些先验引导下，本文构建了包含几何感知正则化的优化流程，该流程可稳定学习过程并确保蒙皮权重平滑、结构连贯。G-Skin还能灵活泛化到为缓解动画诱导渲染伪影而设计的3D高斯表示增强变体。大量实验验证了本文方法的有效性，表明其相较于现有最先进方法具有明显优势。项目页面：this https URL。
英文摘要
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.
