This is the release of MSG-Net for the paper Depth Map Super-Resolution by Deep Multi-Scale Guidance in ECCV16. It comes with 4 trained networks (x2, x4, x8, x16) and 3 testing sets (A, B, C).
For more details, please visit the project page .
The codes are based on caffe and Matlab.
You need to install caffe and remeber to complie matcaffe. You can put the folder MSGNet-release in caffe/examples. Finally, you need to get into the the directory of examples/MSGNet-release, and run MSGNet.m.
Our RGBD training set consists of 58 RGBD images from MPI Sintel depth dataset, and 34 RGBD images from Middlebury dataset. 82 images are used for training and 10 images (frames 1, 20, 28, 58, 64, 66, 69, 73, 75 and 79) are used for validation.
All code is provided for research purposes only and without any warranty. Any commercial use requires our consent. When using the code and/or training data in your research work, please cite the following paper:
"T.-W. Hui, C. C. Loy and X. Tang, Depth Map Super-Resolution by Deep Multi-Scale Guidance, pp. 353–369, ECCV16".