BiDRN: Binarized 3D Whole-body Human Mesh Recovery

ICLR 2025 Conference Submission315 Authors

Keywords: 3D whole-body human mesh recovery, Binarization

TL;DR: BiDRN is the first work to study the binarization of the 3D whole-body human mesh recovery problem.

Abstract: 3D whole-body human mesh recovery aims to reconstruct the 3D human body, face, and hands from a single image. Although powerful deep learning models have achieved accurate estimation in this task, they require enormous memory and computational resources. Consequently, these methods can hardly be deployed on resource-limited edge devices. In this work, we propose a Binarized Dual Residual Network (BiDRN), a novel quantization method designed to estimate the 3D human body, face, and hands parameters efficiently. Specifically, we design a basic unit Binarized Dual Residual Block (BiDRB) composed of Local Convolution Residual (LCR) and Block Residual (BR), which can preserve as much full-precision information as possible. For LCR, we further generalize it to four kinds of convolutional modules so that full-precision information can be propagated even across mismatched dimensions when reshaping features. Additionally, we also binarize the face and hands box-prediction network as Binarized BoxNet, which further reduces the model redundancy. Comprehensive quantitative and qualitative experiments demonstrate the effectiveness of BiDRN, which has a significant improvement over state-of-the-art binarization algorithms. Moreover, our BiDRN achieves comparable performance with the full-precision method Hand4Whole while using only **22.1%** parameters and **14.8%** operations. We will release all the code and pretrained models.

Primary Area: applications to computer vision, audio, language, and other modalities

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 315