2023/12/14 by Hui EnPang, EnPang, Hui, Zhongang Cai +11
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Hand Gesture Recognition Systems #Human Pose and Action Recognition #Video Surveillance and Tracking Methods
paper · pdf · doi:10.48550/arxiv.2312.08730
openalex publication_date 2023/12/14 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Whole-body pose and shape estimation aims to jointly predict different behaviors (e.g., pose, hand gesture, facial expression) of the entire human body from a monocular image. Existing methods often exhibit degraded performance under the complexity of in-the-wild scenarios. We argue that the accuracy and reliability of these models are significantly affected by the quality of the predicted bounding box, e.g., the scale and alignment of body parts. The natural discrepancy between the ideal bounding box annotations and model detection results is particularly detrimental to the performance of whole-body pose and shape estimation. In this paper, we propose a novel framework to enhance the robustness of whole-body pose and shape estimation. Our framework incorporates three new modules to address the above challenges from three perspectives: 1) Localization Module enhances the model's awareness of the subject's location and semantics within the image space. 2) Contrastive Feature Extraction Module encourages the model to be invariant to robust augmentations by incorporating contrastive loss with dedicated positive samples. 3) Pixel Alignment Module ensures the reprojected mesh from the predicted camera and body model parameters are accurate and pixel-aligned. We perform comprehensive experiments to demonstrate the effectiveness of our proposed framework on body, hands, face and whole-body benchmarks. Codebase is available at \urlhttps://github.com/robosmplx/robosmplx.