Neural-Network-Based Photometric Stereo for 3D Surface Reconstruction

2006 ◽  
Author(s):  
Wen-Chang Cheng
Keyword(s):  
Neural Network ◽  
Surface Reconstruction ◽  
Photometric Stereo ◽  
3D Surface Reconstruction ◽  
3D Surface

scholarly journals Pay Attention to Devils: A Photometric Stereo Network for Better Details

2020 ◽  
Author(s):  
Yakun Ju ◽  
Kin-Man Lam ◽  
Yang Chen ◽  
Lin Qi ◽  
Junyu Dong
Keyword(s):  
Neural Network ◽  
State Of The Art ◽  
Photometric Stereo ◽  
Normal Map ◽  
Surface Normal ◽  
3D Surface ◽  
Surface Reconstructions ◽  
Higher Weights

We present an attention-weighted loss in a photometric stereo neural network to improve 3D surface recovery accuracy in complex-structured areas, such as edges and crinkles, where existing learning-based methods often failed. Instead of using a uniform penalty for all pixels, our method employs the attention-weighted loss learned in a self-supervise manner for each pixel, avoiding blurry reconstruction result in such difficult regions. The network first estimates a surface normal map and an adaptive attention map, and then the latter is used to calculate a pixel-wise attention-weighted loss that focuses on complex regions. In these regions, the attention-weighted loss applies higher weights of the detail-preserving gradient loss to produce clear surface reconstructions. Experiments on real datasets show that our approach significantly outperforms traditional photometric stereo algorithms and state-of-the-art learning-based methods.

Sign in / Sign up

Export Citation Format

Share Document