[论文] GaussiAnimate: Reconstruct and Rig Animatable Categories with Level of Dynamics

## 论文概要 **研究领域**: AI **作者**: Jiaxin Wang, Dongxin Lyu, Zeyu Cai **发布时间**: 2025-04-10 **arXiv**: [2504.07091](https://arxiv.org/abs/2504.07091) ## 中文摘要 自由形态骨骼能够紧密贴合表面，有效捕捉非刚性形变，但缺乏直观控制所需的运动学结构。为此，我们提出了一种名为"Skelebones"的脚手架-蒙皮绑定系统，包含三个关键步骤：(1) 骨骼：将时间一致的可变形高斯压缩为自由形态骨骼，近似非刚性表面形变；(2) 骨架：从规范高斯中提取平均曲率骨架并随时间细化，确保类别无关、运动自适应且拓扑正确的运动学结构；(3) 绑定：通过非参数化部件运动匹配（PartMM）将骨架与骨骼绑定，通过匹配、检索和融合现有骨骼运动来合成新的骨骼运动。这三个步骤共同使我们能够将4D形状的动态层级压缩为既可控又具表现力的紧凑skelebones。我们在合成和真实数据集上验证了该方法，在未见过姿态的重新动画性能上实现了显著提升——相比线性混合蒙皮（LBS）提高17.3% PSNR，相比Bag-of-Bones（BoB）提高21.7%——同时保持出色的重建保真度，尤其对于展现复杂非刚性表面动态的角色。我们的部件运动匹配算法对高斯表示和网格表示都表现出强泛化能力，尤其在低数据量情况下（约1000帧），相比鲁棒LBS实现48.4%的RMSE改进，并超过基于GRU和MLP的学习方法20%以上。 ## 原文摘要 Free-form bones, that conform closely to the surface, can effectively capture non-rigid deformations, but lack a kinematic structure necessary for intuitive control. Thus, we propose a Scaffold-Skin Rigging System, termed "Skelebones", with three key steps: (1) Bones: compress temporally-consistent deformable Gaussians into free-form bones, approximating non-rigid surface deformations; (2) Skeleton: extract a Mean Curvature Skeleton from canonical Gaussians and refine it temporally, ensuring a category-agnostic, motion-adaptive, and topology-correct kinematic structure; (3) Binding: bind the skeleton and bones via non-parametric partwise motion matching (PartMM), synthesizing novel bone motions by matching, retrieving, and blending existing ones. Collectively, these three steps enable us to compress the Level of Dynamics of 4D shapes into compact skelebones that are both controllable and expressive. We validate our approach on both synthetic and real-world datasets, achieving significant improvements in reanimation performance across unseen poses-with 17.3% PSNR gains over Linear Blend Skinning (LBS) and 21.7% over Bag-of-Bones (BoB)-while maintaining excellent reconstruction fidelity, particularly for characters exhibiting complex non-rigid surface dynamics. Our Partwise Motion Matching algorithm demonstrates strong generalization to both Gaussian and mesh representations, especially under low-data regime (~1000 frames), achieving 48.4% RMSE improvement over robust LBS and outperforming GRU- and MLP-based learning methods by >20%. --- *自动采集于 2025-04-11* #论文 #arXiv #AI #小凯