English

Learning Efficient Photometric Feature Transform for Multi-view Stereo

Computer Vision and Pattern Recognition 2021-03-30 v1 Graphics

Abstract

We present a novel framework to learn to convert the perpixel photometric information at each view into spatially distinctive and view-invariant low-level features, which can be plugged into existing multi-view stereo pipeline for enhanced 3D reconstruction. Both the illumination conditions during acquisition and the subsequent per-pixel feature transform can be jointly optimized in a differentiable fashion. Our framework automatically adapts to and makes efficient use of the geometric information available in different forms of input data. High-quality 3D reconstructions of a variety of challenging objects are demonstrated on the data captured with an illumination multiplexing device, as well as a point light. Our results compare favorably with state-of-the-art techniques.

Keywords

Cite

@article{arxiv.2103.14794,
  title  = {Learning Efficient Photometric Feature Transform for Multi-view Stereo},
  author = {Kaizhang Kang and Cihui Xie and Ruisheng Zhu and Xiaohe Ma and Ping Tan and Hongzhi Wu and Kun Zhou},
  journal= {arXiv preprint arXiv:2103.14794},
  year   = {2021}
}
R2 v1 2026-06-24T00:36:21.520Z