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

Co-Evolution of Pose and Mesh for 3D Human Body Estimation from Video

About

Despite significant progress in single image-based 3D human mesh recovery, accurately and smoothly recovering 3D human motion from a video remains challenging. Existing video-based methods generally recover human mesh by estimating the complex pose and shape parameters from coupled image features, whose high complexity and low representation ability often result in inconsistent pose motion and limited shape patterns. To alleviate this issue, we introduce 3D pose as the intermediary and propose a Pose and Mesh Co-Evolution network (PMCE) that decouples this task into two parts: 1) video-based 3D human pose estimation and 2) mesh vertices regression from the estimated 3D pose and temporal image feature. Specifically, we propose a two-stream encoder that estimates mid-frame 3D pose and extracts a temporal image feature from the input image sequence. In addition, we design a co-evolution decoder that performs pose and mesh interactions with the image-guided Adaptive Layer Normalization (AdaLN) to make pose and mesh fit the human body shape. Extensive experiments demonstrate that the proposed PMCE outperforms previous state-of-the-art methods in terms of both per-frame accuracy and temporal consistency on three benchmark datasets: 3DPW, Human3.6M, and MPI-INF-3DHP. Our code is available at https://github.com/kasvii/PMCE.

Yingxuan You, Hong Liu, Ti Wang, Wenhao Li, Runwei Ding, Xia Li• 2023

Related benchmarks

TaskDatasetResultRank
3D Human Pose EstimationHuman3.6M (test)
MPJPE (Average)53.5
547
3D Human Pose Estimation3DPW (test)
PA-MPJPE52.3
505
3D Human Mesh Recovery3DPW (test)
PA-MPJPE46.7
264
Human Mesh Recovery3DPW
PA-MPJPE47.05
123
3D Human Mesh RecoveryHuman3.6M (test)
PA-MPJPE37.7
120
Human Mesh RecoveryHuman3.6M
Reconstruction Error54.58
47
Human Mesh ReconstructionMPI-INF-3DHP (test)
MPJPE79.7
36
Human Mesh RecoveryMPI-INF-3DHP
MPJPE80.46
35
Showing 8 of 8 rows

Other info

Follow for update