AniGen：统一的S³场用于可动画化的3D资产生成
AniGen: Unified $S^3$ Fields for Animatable 3D Asset Generation
AI总结：
AniGen通过统一的S³场生成可动画化的3D资产，解决传统方法在生成后制作rig时的不稳定性问题，提升动画质量和泛化能力。
摘要：
可动画化的3D资产，定义为配备关节骨骼和皮肤权重的几何体，是交互图形、具身代理和动画生产的基础。尽管最近的3D生成模型能从图像合成视觉逼真的形状，但结果通常是静态的。通过事后自动 rigging 获取可用的rig 是脆弱且往往产生与生成几何体拓扑不一致的骨骼。我们提出了AniGen，一个统一的框架，直接根据单张图像生成可动画的3D资产。我们的关键见解是将形状、骨骼和皮肤表示为互为一致的S³场（形状、骨骼、皮肤），定义在共享的空间域上。为了使这些场的鲁棒学习成为可能，我们引入了两项技术创新：(i) 一种衰减置信度的骨骼场，明确处理在Voronoi边界处骨骼预测的几何模糊性；(ii) 一种双皮肤特征场，将皮肤权重与特定关节数量解耦，允许固定架构的网络预测任意复杂度的rig。基于一个两阶段的流匹配流水线，AniGen首先合成稀疏的结构支架，然后在结构化潜在空间中生成密集的几何体和运动。广泛的实验表明，AniGen在rig有效性及动画质量上显著优于最先进的顺序基线，在野外图像上泛化效果良好，涵盖动物、人形和机械等多种类别。Homepage: https://yihua7.github.io/AniGen-web/
英文摘要：
Animatable 3D assets, defined as geometry equipped with an articulated skeleton and skinning weights, are fundamental to interactive graphics, embodied agents, and animation production. While recent 3D generative models can synthesize visually plausible shapes from images, the results are typically static. Obtaining usable rigs via post-hoc auto-rigging is brittle and often produces skeletons that are topologically inconsistent with the generated geometry. We present AniGen, a unified framework that directly generates animate-ready 3D assets conditioned on a single image. Our key insight is to represent shape, skeleton, and skinning as mutually consistent $S^3$ Fields (Shape, Skeleton, Skin) defined over a shared spatial domain. To enable the robust learning of these fields, we introduce two technical innovations: (i) a confidence-decaying skeleton field that explicitly handles the geometric ambiguity of bone prediction at Voronoi boundaries, and (ii) a dual skin feature field that decouples skinning weights from specific joint counts, allowing a fixed-architecture network to predict rigs of arbitrary complexity. Built upon a two-stage flow-matching pipeline, AniGen first synthesizes a sparse structural scaffold and then generates dense geometry and articulation in a structured latent space. Extensive experiments demonstrate that AniGen substantially outperforms state-of-the-art sequential baselines in rig validity and animation quality, generalizing effectively to in-the-wild images across diverse categories including animals, humanoids, and machinery. Homepage: https://yihua7.github.io/AniGen-web/
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
