Dual networks based 3D Multi-Person Pose Estimation from Monocular Video

Abstract

Monocular 3D human pose estimation has made progress in recent years. Most of the methods focus on single persons, which estimate the poses in the person-centric coordinates, i.e., the coordinates based on the center of the target person. Hence, these methods are inapplicable for multi-person 3D pose estimation, where the absolute coordinates (e.g., the camera coordinates) are required. Moreover, multi-person pose estimation is more challenging than single pose estimation, due to inter-person occlusion and close human interactions. Existing top-down multi-person methods rely on human detection (i.e., top-down approach), and thus suffer from the detection errors and cannot produce reliable pose estimation in multi-person scenes. Meanwhile, existing bottom-up methods that do not use human detection are not affected by detection errors, but since they process all persons in a scene at once, they are prone to errors, particularly for persons in small scales. To address all these challenges, we propose the integration of top-down and bottom-up approaches to exploit their strengths. Our top-down network estimates human joints from all persons instead of one in an image patch, making it robust to possible erroneous bounding boxes. Our bottom-up network incorporates human-detection based normalized heatmaps, allowing the network to be more robust in handling scale variations. Finally, the estimated 3D poses from the top-down and bottom-up networks are fed into our integration network for final 3D poses. To address the common gaps between training and testing data, we do optimization during the test time, by refining the estimated 3D human poses using high-order temporal constraint, re-projection loss, and bone length regularizations. Our evaluations demonstrate the effectiveness of the proposed method. Code and models are available: https://github.com/3dpose/3D-Multi-Person-Pose.

arXiv commentAccepted by TPAMI 2022. arXiv admin note: substantial text overlap with arXiv:2104.01797

References in corpus (12)

• VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera
• OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields
• LCR-Net++: Multi-person 2D and 3D Pose Detection in Natural Images
• Exploiting temporal information for 3D pose estimation
• XNect: Real-time Multi-Person 3D Motion Capture with a Single RGB Camera
• Cascaded deep monocular 3D human pose estimation with evolutionary training data
• Multi-task Deep Learning for Real-Time 3D Human Pose Estimation and Action Recognition
• Self-supervised Keypoint Correspondences for Multi-Person Pose Estimation and Tracking in Videos
• PhysCap: Physically Plausible Monocular 3D Motion Capture in Real Time
• Inference Stage Optimization for Cross-scenario 3D Human Pose Estimation
• ArtTrack: Articulated Multi-person Tracking in the Wild
• Multi-Scale Networks for 3D Human Pose Estimation with Inference Stage Optimization

Cited by in corpus (1)

• Deep learning for 3D human pose estimation and mesh recovery: A survey