Part-wise Normal Prediction divides an image into each body part through a matrix using keypoints. This helps in predicting detailed normal vectors for each body part with minimal computation.
This is an unofficial official pytorch implementation of the following paper: Y. Deng, J. Yang, S. Xu, D. Chen, Y. Jia, and X. Tong, Accurate 3D Face Reconstruction with Weakly-Supervised Learning: ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback