This repo implements the training and testing of depth upsampling networks for "Learning Scene Structure Guidance via Cross-Task Knowledge Transfer for Single Depth Super-Resolution" by Baoli Sun, Xinchen Ye, and et al. at DLUT.

The proposed Cross-Task Knowledge Transfer framework

We will update the code soon.

Citation

If this codebase or our method helps your research, please cite:

@InProceedings{Sun2021cvpr, author = {Baoli Sun, Xinchen Ye, Baopu Li, Haojie Li, Zhihui Wang, Rui Xu}, title = {Learning Scene Structure Guidance via Cross-Task Knowledge Transfer for Single Depth Super-Resolution}, booktitle = {{IEEE} Conference on Computer Vision and Pattern Recognition, {CVPR}}, year = {2021}, }