We generate high-resolution depth estimations from a single image by using pre-trained networks in different resolutions.
Check out the project web page here: http://yaksoy.github.io/highresdepth/
Our code and trained models are available: https://github.com/compphoto/BoostingMonocularDepth
Video by Ari Blondal, an undergraduate student at SFU. Check out his Youtube channel: https://www.youtube.com/user/ariblondal
S. Mahdi H. Miangoleh, Sebastian Dille, Long Mai, Sylvain Paris, and Yağız Aksoy, "Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Merging", Proc. CVPR, 2021