This repository contains the code for our papers:

Songyou Peng, Bjoern Haefner, Yvain Queau and Daniel Cremers, "Depth Super-Resolution Meets Uncalibrated Photometric Stereo", In IEEE Conference on Computer Vision (ICCV) Workshop, 2017.

and

Bjoern Haefner*, Songyou Peng*, Alok Verma*, Yvain Queau and Daniel Cremers, "Photometric Depth Super-Resolution", IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2019. (* equally contributed)

A CUDA version code is also available here.

• Super-resolution RGB images (at least 4 images)
• Super-resolution binary mask
• Low-resolution depth images (1 image is fine, same size as RGB image is also fine)
• Intrinsic matrix (containing the focal length and principle points of the RGB images)
• [Optional] Downsampling matrix (you can aquire with getDownsampleMat.m)

All the real-world data can be found at this link.

• MATLAB (tested and working in R2015b and later versions)
• [Optional] CMG solver (recommended)

If you use this code, please cite our papers:

@inproceedings{peng2017iccvw,
 author =  {Songyou Peng and Bjoern Haefner and Yvain Qu{\'e}au and Daniel Cremers},
 title = {{Depth Super-Resolution Meets Uncalibrated Photometric Stereo}},
 year = {2017},
 booktitle = {IEEE International Conference on Computer Vision (ICCV) Workshop},
}

and

@inproceedings{haefner2018pdsr,
 author =  {Bjoern Haefner and Songyou Peng and Alok Verma and Yvain Qu{\'e}au and Daniel Cremers},
 title = {Photometic Depth Super-Resolution},
 year = {2019},
 booktitle = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
}

Contact Songyou Peng ✉️ for questions, comments and reporting bugs.