Building animatable and editable models of clothed humans from raw 3D scans and poses is a challenging problem. Existing reposing methods suffer from the limited expressiveness of Linear Blend Skinning (LBS), require costly mesh extraction to generate each new pose, and typically do not preserve surface correspondences across different poses. In this work, we introduce Invertible Neural Skinning (INS) to address these shortcomings. To maintain correspondences, we propose a Pose-conditioned Invertible Network (PIN) architecture, which extends the LBS process by learning additional pose-varying deformations. Next, we combine PIN with a differentiable LBS module to build an expressive and end-to-end Invertible Neural Skinning (INS) pipeline. We demonstrate the strong performance of our method by outperforming the state-of-the-art reposing techniques on clothed humans and preserving surface correspondences, while being an order of magnitude faster. We also perform an ablation study, which shows the usefulness of our pose-conditioning formulation, and our qualitative results display that INS can rectify artefacts introduced by LBS well. See our webpage for more details: https://yashkant.github.io/invertible-neural-skinning/

翻译：从原始三维扫描数据和姿态中构建可动画化且可编辑的穿衣人体模型是一项具有挑战性的问题。现有的重姿态方法受限于线性混合蒙皮（LBS）的表达能力不足，需要昂贵的网格提取来生成每个新姿态，并且通常无法在不同姿态间保持表面对应关系。在本工作中，我们提出可逆神经蒙皮（INS）以解决这些缺陷。为维持对应关系，我们提出一种姿态条件可逆网络（PIN）架构，通过学习额外的姿态变化形变来扩展LBS流程。随后，我们将PIN与可微分LBS模块相结合，构建了一个富有表达能力且端到端的可逆神经蒙皮（INS）管线。我们通过超越现有最先进的穿衣人体重姿态技术并保持表面对应关系，同时速度提升一个数量级，证明了我们方法的强大性能。我们还进行了消融实验，展示了姿态条件公式的有效性，定性结果表明INS能很好地修正LBS引入的伪影。详情请参阅我们的网页：https://yashkant.github.io/invertible-neural-skinning/