用分布表示法生成高保真3D人体动画，细节更自然。
Human Geometry Distribution for 3D Animation Generation
- 用紧凑的概率分布表示人体几何，提升生成效率与质量。
- 生成动画在短时过渡中多样，长时保持身份一致性，用户评分提升2.2倍。
- 适合需要精细人体动作模拟的影视、游戏开发场景。
生成逼真的3D人体几何动画仍具挑战，需在数据有限的情况下建模自然的服装动态与细粒度几何细节。为此，我们提出两项新设计：首先，采用紧凑的基于分布的潜在表征，实现高效高质量的几何生成，并建立了比SMPL更均匀的人体与角色几何映射关系；其次，提出一种生成式动画模型，充分挖掘有限运动数据的多样性。模型聚焦短时过渡，通过身份条件设计保持长时一致性。整体方法为两阶段框架：第一阶段学习潜在空间，第二阶段在该空间内生成动画。实验表明，所提潜在空间生成的人体几何质量显著优于此前方法（Chamfer距离降低90%）；动画模型合成的动画在细节与自然性上表现优异（用户评估得分提高2.2倍），各项指标均达到最优。
原文摘要 · Abstract (English)
Generating realistic human geometry animations remains a challenging task, as it requires modeling natural clothing dynamics with fine-grained geometric details under limited data. To address these challenges, we propose two novel designs. First, we propose a compact distribution-based latent representation that enables efficient and high-quality geometry generation. We improve upon previous work by establishing a more uniform mapping between SMPL and avatar geometries. Second, we introduce a generative animation model that fully exploits the diversity of limited motion data. We focus on short-term transitions while maintaining long-term consistency through an identity-conditioned design. These two designs formulate our method as a two-stage framework: the first stage learns a latent space, while the second learns to generate animations within this latent space. We conducted experiments on both our latent space and animation model. We demonstrate that our latent space produces high-fidelity human geometry surpassing previous methods ($90\%$ lower Chamfer Dist.). The animation model synthesizes diverse animations with detailed and natural dynamics ($2.2 \times$ higher user study score), achieving the best results across all evaluation metrics.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。