用人体测量数据统一人体网格形状，提升三维人体建模一致性与精度
Leveraging Anthropometric Measurements to Improve Human Mesh Estimation and Ensure Consistent Body Shapes
- 引入裁缝常用的人体测量数据，转换为人体网格的基础形状参数
- 在ASPset和fit3D数据集上，将关键点误差降低超30毫米
- 适配现有模型即可实现更稳定的人体形状，适合视频中人体建模应用
一个人的基本身体形态（即T姿态下的形态）在单个视频中保持不变。然而，大多数当前最优的人体网格估计（HME）模型对每一帧输出略有不同的基础身体形态，导致不一致。我们发现，当前最优的3D人体姿态估计（HPE）模型在关键点定位精度上优于HME模型。为此，我们提出A2B模型，将人体测量数据（如裁缝所测）转换为人体网格模型的基础形状参数。通过结合A2B输出与HPE模型的关键点，利用逆运动学生成更优且一致的人体网格。我们在ASPset和fit3D等挑战性数据集上评估，相比当前最优的HME模型，平均关键点位置误差（MPJPE）降低超过30毫米。此外，将现有HME模型中身体参数的估计替换为A2B结果，不仅提升了性能，还保证了身体形状的一致性。
原文摘要 · Abstract (English)
The basic body shape (i.e., the body shape in T-pose) of a person does not change within a single video. However, most SOTA human mesh estimation (HME) models output a slightly different, thus inconsistent basic body shape for each video frame. Furthermore, we find that SOTA 3D human pose estimation (HPE) models outperform HME models regarding the precision of the estimated 3D keypoint positions. We solve the problem of inconsistent body shapes by leveraging anthropometric measurements like taken by tailors from humans. We create a model called A2B that converts given anthropometric measurements to basic body shape parameters of human mesh models. We obtain superior and consistent human meshes by combining the A2B model results with the keypoints of 3D HPE models using inverse kinematics. We evaluate our approach on challenging datasets like ASPset or fit3D, where we can lower the MPJPE by over 30 mm compared to SOTA HME models. Further, replacing estimates of the body shape parameters from existing HME models with A2B results not only increases the performance of these HME models, but also guarantees consistent body shapes.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。