5 papers
Aerial Multi-View Stereo via Adaptive Depth Range Inference and Normal Cues
Yimei Liu, Yakun Ju, Yuan Rao +4
Three-dimensional digital urban reconstruction from multi-view aerial images is a critical application where deep multi-view stereo (MVS) methods outperform traditional techniques.…
FNIN: A Fourier Neural Operator-based Numerical Integration Network for Surface-form-gradients
Jiaqi Leng, Yakun Ju, Yuanxu Duan +4
Surface-from-gradients (SfG) aims to recover a three-dimensional (3D) surface from its gradients. Traditional methods encounter significant challenges in achieving high accuracy an…
Image Gradient-Aided Photometric Stereo Network
Kaixuan Wang, Lin Qi, Shiyu Qin +4
Photometric stereo (PS) endeavors to ascertain surface normals using shading clues from photometric images under various illuminations. Recent deep learning-based PS methods often…
RMAFF-PSN: A Residual Multi-Scale Attention Feature Fusion Photometric Stereo Network
Kai Luo, Yakun Ju, Lin Qi +2
Predicting accurate normal maps of objects from two-dimensional images in regions of complex structure and spatial material variations is challenging using photometric stereo metho…
Deep Learning Methods for Calibrated Photometric Stereo and Beyond
Yakun Ju, Kin-Man Lam, Wuyuan Xie +3
Photometric stereo recovers the surface normals of an object from multiple images with varying shading cues, i.e., modeling the relationship between surface orientation and intensi…