Limitations of (Procrustes) Alignment in Assessing Multi-Person Human Pose and Shape Estimation
Not on the map. Why?
Abstract (arXiv)
We delve into the challenges of accurately estimating 3D human pose and shape in video surveillance scenarios. Beginning with the advocacy for metrics like W-MPJPE and W-PVE, which omit the (Procrustes) realignment step, to improve model evaluation, we then introduce RotAvat. This technique aims to enhance these metrics by refining the alignment of 3D meshes with the ground plane. Through qualitative comparisons, we demonstrate RotAvat's effectiveness in addressing the limitations of existing aproaches.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 12 of its 12 references that are in the map. First posted on arXiv 25 Sep 2024.
Builds on
12 of 12 references.
References · 12
- 2020HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimationcited by 307
- 2021PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loopcited by 250
- 2022CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimationcited by 238
- 2023BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motioncited by 236
- 2020Monocular, One-stage, Regression of Multiple 3D Peoplecited by 218
- 2021GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Camerascited by 153
- 2021Putting People in their Place: Monocular Regression of 3D People in Depthcited by 142
- 2021SPEC: Seeing People in the Wild with an Estimated Cameracited by 135
- 20233D Human Pose Estimation via Intuitive Physicscited by 103
- 2023TRACE: 5D Temporal Regression of Avatars with Dynamic Cameras in 3D Environmentscited by 91
- 2022MIME: Human-Aware 3D Scene Generationcited by 57
- 2023HybrIK-X: Hybrid Analytical-Neural Inverse Kinematics for Whole-body Mesh Recoverycited by 49
Built on by
Not cited yet.