On October 6th 2025 at 16:00, Ran Zhao will defend their PhD entitled āDEEP LEARNING-BASED HUMAN POSTURE NORMALIZATION AND AUTOMATIC ANTHROPOMETRIC MEASUREMENTā.
Everybody is invited to attend the presentation in room D.2.01 or online via thisĀ link.
Accurate and user-friendly anthropometric measurement remains a major challenge in computer vision, as existing approaches typically require controlled scanning conditions, standard postures, or unclothed bodies. These constraints limit their usability in practical scenarios.
This thesis proposes a sequence of deep learning-based solutions to overcome these limitations. We first introduce OrienNormNet, an iterative network for robust orientation normalization, ensuring that scans are consistently aligned without manual preprocessing. Building on this, PoseNormNet is presented as the first posture normalization framework that transforms arbitrarily posed scans into a canonical T-pose while preserving identity details, removing the need for skeleton rigging. Next, W2H-Net demonstrates the feasibility of directly estimating the waist-to-hip ratio from partial dressed scans, showing that reliable indicators can be derived even from incomplete data. Finally, MeasureXpert provides a breakthrough toward real-world usability: it enables automatic extraction of anthropometric measurements from only two unregistered, partial, and clothed scans acquired in arbitrary poses.
To support these developments, the BWM dataset was synthesized for training, validation, and evaluation. Comprehensive experiments on both synthetic and real-world data confirm the effectiveness and robustness of the proposed methods. Collectively, the contributions progressively address key challenges related to cost, posture, and clothing, moving the field closer to practical, flexible, and accessible body measurement solutions.
The algorithms presented in this thesis have been disseminated through prestigious journals and conferences, demonstrating a modest yet meaningful impact on both academic research and industrial applications.
