HAHA：带纹理网格先验的高自由度高斯人体化身
HAHA: Highly Articulated Gaussian Human Avatars with Textured Mesh Prior
AI总结：
本研究提出HAHA方法，结合高斯泼溅与纹理网格先验，从单目视频生成可驱动的高自由度人体化身，仅在必要区域用高斯，大幅减少高斯数量的同时实现了更优的新姿态重建效果。
摘要：
我们提出了HAHA——一种从单目输入视频生成可驱动人体化身的新方法。该方法通过学习高斯泼溅（Gaussian splatting）与纹理网格之间的使用权衡，实现高效且高保真的渲染。我们验证了其在驱动和渲染由SMPL-X参数化模型控制的全身人体化身方面的高效性。我们的模型学会仅在SMPL-X网格的必要区域（如头发和网格外衣物）应用高斯泼溅。这使得表示整个人体化身所需的高斯数量极少，且减少了渲染伪影。借此我们能够处理传统方法常忽略的手指等小身体部位的动画。我们在两个公开数据集SnapshotPeople和X-Humans上验证了方法的有效性。在SnapshotPeople上，我们的方法重建质量与当前最优水平相当，而使用的高斯数量不到其三分之一。在X-Humans的新姿态任务上，HAHA在定量和定性指标上均优于此前的最优方法。
英文摘要：
We present HAHA - a novel approach for animatable human avatar generation from monocular input videos. The proposed method relies on learning the trade-off between the use of Gaussian splatting and a textured mesh for efficient and high fidelity rendering. We demonstrate its efficiency to animate and render full-body human avatars controlled via the SMPL-X parametric model. Our model learns to apply Gaussian splatting only in areas of the SMPL-X mesh where it is necessary, like hair and out-of-mesh clothing. This results in a minimal number of Gaussians being used to represent the full avatar, and reduced rendering artifacts. This allows us to handle the animation of small body parts such as fingers that are traditionally disregarded. We demonstrate the effectiveness of our approach on two open datasets: SnapshotPeople and X-Humans. Our method demonstrates on par reconstruction quality to the state-of-the-art on SnapshotPeople, while using less than a third of Gaussians. HAHA outperforms previous state-of-the-art on novel poses from X-Humans both quantitatively and qualitatively.
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。
