$E^{3}$Gen：高效、富有表现力且可编辑的虚拟人生成
$E^{3}$Gen: Efficient, Expressive and Editable Avatars Generation
AI总结：
本文提出$E^3$Gen，通过生成式UV特征平面表示将3D Gaussian编码至SMPL-X定义的2D空间，并引入部件感知变形模块，实现了高效、富有表现力且可编辑的数字虚拟人生成。
摘要：
本文旨在引入3D Gaussian以实现高效、富有表现力且可编辑的数字虚拟人生成。该任务面临两大挑战：(1) 3D Gaussian的非结构化特性使其与当前的生成管线不兼容；(2) 在涉及多主体训练的生成设置中，3D Gaussian的富有表现力的动画仍未被探索。本文提出一种名为$E^3$Gen的新型虚拟人生成方法，以有效应对这些挑战。首先，我们提出一种新型生成式UV特征平面表示，将非结构化的3D Gaussian编码到由SMPL-X参数化模型定义的结构化2D UV空间中。这种新型表示不仅保留了原始3D Gaussian的表示能力，还引入了主体间的共享结构，从而实现对扩散模型的生成式学习。为解决第二个挑战，我们提出一个部件感知变形模块，以实现鲁棒且准确的全身富有表现力的姿态控制。大量实验表明，我们的方法在虚拟人生成中取得了优越的性能，并实现了富有表现力的全身姿态控制与编辑。我们的项目页面是 https://olivia23333.github.io/E3Gen。
英文摘要：
This paper aims to introduce 3D Gaussian for efficient, expressive, and editable digital avatar generation. This task faces two major challenges: (1) The unstructured nature of 3D Gaussian makes it incompatible with current generation pipelines; (2) the expressive animation of 3D Gaussian in a generative setting that involves training with multiple subjects remains unexplored. In this paper, we propose a novel avatar generation method named $E^3$Gen, to effectively address these challenges. First, we propose a novel generative UV features plane representation that encodes unstructured 3D Gaussian onto a structured 2D UV space defined by the SMPL-X parametric model. This novel representation not only preserves the representation ability of the original 3D Gaussian but also introduces a shared structure among subjects to enable generative learning of the diffusion model. To tackle the second challenge, we propose a part-aware deformation module to achieve robust and accurate full-body expressive pose control. Extensive experiments demonstrate that our method achieves superior performance in avatar generation and enables expressive full-body pose control and editing. Our project page is https://olivia23333.github.io/E3Gen.
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。
