BinaryHPE: 3D Human Pose and Shape Estimation via Binarization
This work addresses deployment challenges on resource-limited edge devices for researchers and practitioners in computer vision, though it is incremental as it builds on existing binarization techniques.
The paper tackles the problem of high memory and computational requirements in 3D human pose and shape estimation by proposing BinaryHPE, a binarization method that achieves comparable performance to full-precision methods while using only 22.1% parameters and 14.8% operations.
3D human pose and shape estimation (HPE) 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 BinaryHPE, a novel binarization method designed to estimate the 3D human body, face, and hands parameters efficiently. Specifically, we propose a novel binary backbone called Binarized Dual Residual Network (BiDRN), designed to retain as much full-precision information as possible. Furthermore, we propose the Binarized BoxNet, an efficient sub-network for predicting face and hands bounding boxes, which further reduces model redundancy. Comprehensive quantitative and qualitative experiments demonstrate the effectiveness of BinaryHPE, which has a significant improvement over state-of-the-art binarization algorithms. Moreover, our BinaryHPE 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.