学习可局部编辑的虚拟人
Learning Locally Editable Virtual Humans
AI总结：
本研究提出结合神经场与蒙皮网格的混合表示及端到端网络，构建特征码本存储局部特征，实现神经化身的生成、适配与局部编辑，还发布CustomHumans数据集，实验证明性能优于现有最优方法。
摘要：
本文提出一种新型混合表示与端到端可训练网络架构，用于建模完全可编辑、可定制的神经化身。该表示结合了神经场的建模能力与蒙皮网格的易用性和固有3D一致性，是本研究的核心。为此，我们构建了一个可训练特征码本，用于在可变形人体模型的顶点上存储局部几何与纹理特征，从而利用其在关节运动下的一致拓扑结构。随后，该表示被应用于生成式自动解码器架构中，该架构可适配未见过的扫描数据，并采样生成具有不同外观与几何形态的逼真化身。此外，我们的表示支持通过在3D资产间交换局部特征实现局部编辑。为验证我们的化身创建与编辑方法，我们构建了一个名为CustomHumans的新型高质量数据集用于训练与评估。我们的实验从定量与定性层面表明，与现有最优方法相比，我们的方法能生成多样化的细节丰富的化身，并取得更优的模型拟合性能。我们的代码与数据集可在https://custom-humans.github.io/获取。
英文摘要：
In this paper, we propose a novel hybrid representation and end-to-end trainable network architecture to model fully editable and customizable neural avatars. At the core of our work lies a representation that combines the modeling power of neural fields with the ease of use and inherent 3D consistency of skinned meshes. To this end, we construct a trainable feature codebook to store local geometry and texture features on the vertices of a deformable body model, thus exploiting its consistent topology under articulation. This representation is then employed in a generative auto-decoder architecture that admits fitting to unseen scans and sampling of realistic avatars with varied appearances and geometries. Furthermore, our representation allows local editing by swapping local features between 3D assets. To verify our method for avatar creation and editing, we contribute a new high-quality dataset, dubbed CustomHumans, for training and evaluation. Our experiments quantitatively and qualitatively show that our method generates diverse detailed avatars and achieves better model fitting performance compared to state-of-the-art methods. Our code and dataset are available at https://custom-humans.github.io/.
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。
