Lightweight Explicit 3D Human Digitization via Normal Integration.

Journal: Sensors (Basel, Switzerland)
PMID:

Abstract

In recent years, generating 3D human models from images has gained significant attention in 3D human reconstruction. However, deploying large neural network models in practical applications remains challenging, particularly on resource-constrained edge devices. This problem is primarily because large neural network models require significantly higher computational power, which imposes greater demands on hardware capabilities and inference time. To address this issue, we can optimize the network architecture to reduce the number of model parameters, thereby alleviating the heavy reliance on hardware resources. We propose a lightweight and efficient 3D human reconstruction model that balances reconstruction accuracy and computational cost. Specifically, our model integrates Dilated Convolutions and the Cross-Covariance Attention mechanism into its architecture to construct a lightweight generative network. This design effectively captures multi-scale information while significantly reducing model complexity. Additionally, we introduce an innovative loss function tailored to the geometric properties of normal maps. This loss function provides a more accurate measure of surface reconstruction quality and enhances the overall reconstruction performance. Experimental results show that, compared with existing methods, our approach reduces the number of training parameters by approximately 80% while maintaining the generated model's quality.

Authors

  • Jiaxuan Liu
    Institute of Biomedical Manufacturing and Life Quality Engineering, School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai, China.
  • Jingyi Wu
    Rehabilitation Hospital affiliated to Fujian University of Traditional Chinese Medicine, Fuzhou, Fujian, China.
  • Ruiyang Jing
    Academy for Engineering and Technology, Fudan University, Shanghai 200433, China.
  • Han Yu
    1Joint NTU-UBC Research Centre of Excellence in Active Living for the Elderly (LILY), Nanyang Technological University, Singapore, 639798 Singapore.
  • Jing Liu
    Department of Ophthalmology, Beijing Hospital, National Center of Gerontology, Institute of Geriatric Medicine, Chinese Academy of Medical Sciences, Beijing, China.
  • Liang Song
    Research Laboratory for Biomedical Optics and Molecular Imaging, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China.