Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

LASOR: Learning Accurate 3D Human Pose and Shape Via Synthetic Occlusion-Aware Data and Neural Mesh Rendering

About

A key challenge in the task of human pose and shape estimation is occlusion, including self-occlusions, object-human occlusions, and inter-person occlusions. The lack of diverse and accurate pose and shape training data becomes a major bottleneck, especially for scenes with occlusions in the wild. In this paper, we focus on the estimation of human pose and shape in the case of inter-person occlusions, while also handling object-human occlusions and self-occlusion. We propose a novel framework that synthesizes occlusion-aware silhouette and 2D keypoints data and directly regress to the SMPL pose and shape parameters. A neural 3D mesh renderer is exploited to enable silhouette supervision on the fly, which contributes to great improvements in shape estimation. In addition, keypoints-and-silhouette-driven training data in panoramic viewpoints are synthesized to compensate for the lack of viewpoint diversity in any existing dataset. Experimental results show that we are among the state-of-the-art on the 3DPW and 3DPW-Crowd datasets in terms of pose estimation accuracy. The proposed method evidently outperforms Mesh Transformer, 3DCrowdNet and ROMP in terms of shape estimation. Top performance is also achieved on SSP-3D in terms of shape prediction accuracy. Demo and code will be available at https://igame-lab.github.io/LASOR/.

Kaibing Yang, Renshu Gu, Maoyu Wang, Masahiro Toyoura, Gang Xu• 2021

Related benchmarks

TaskDatasetResultRank
3D Human Pose Estimation3DPW (test)--
505
3D Human Shape EstimationSSP-3D (test)
PVE (T-SC)14.5
54
3D human shape and pose estimation3DPW
MPJPE-PA57.9
30
3D Human Pose and Shape Estimation3DPW Crowd
MPJPE-PA67.6
6
3D Human Pose and Shape Estimation3DOH50K
MPJPE-PA72.5
6
3D Human Pose and Shape EstimationSSP-3D
PVE-T-SC14.5
5
Showing 6 of 6 rows

Other info

Code

Follow for update