This repository (https://github.com/twhui/MS-Net) is the offical release of MS-Net for our paper Depth Map Super-Resolution by Deep Multi-Scale Guidance in ECCV16. It comes with four trained networks (x2, x4, x8, and x16) one hole-filled RGBD training set, and three hole-filled RGBD testing sets (A, B, and C).

To the best of our knowledge, MS-Net is the FIRST convolution neural network which attempts to upsample depth images.

Another repository for MSG-Net (multi-scale guidance network) is also available.

For more details, please visit my project page.

This software and associated documentation files (the "Software"), and the research paper (Depth Map Super-Resolution by Deep Multi-Scale Guidance) including but not limited to the figures, and tables (the "Paper") are provided for academic research purposes only and without any warranty. Any commercial use requires my consent. When using any parts of the Software or the Paper in your work, please cite the following paper

@InProceedings{hui16msgnet,    
 author = {Tak-Wai Hui and Chen Change Loy and and Xiaoou Tang},    
 title  = {Depth Map Super-Resolution by Deep Multi-Scale Guidance},    
 booktitle  = {Proceedings of European Conference on Computer Vision (ECCV)},    
 pages = {353--369},  
 year = {2016},    
 url = {https://mmlab.ie.cuhk.edu.hk/projects/guidance_SR_depth.html}
}

We train our models using caffe and evaluate the results on Matlab.

You need to install caffe and remeber to complie matcaffe. You can put the folder MSNet-release in caffe/examples. Finally, you need to get into the the directory of examples/MSNet-release/util, and run MSNet.m.

Please refer to MSG-Net.

Testig set is available at the folder MSNet-release/testing sets.