Depth Anything V2 -- large
relative depth, trained on 595K synthetic and 62M+ real unlabelled images

Copyright (c) 2024 TikTok and The University of Hong Kong.
Lihe Yang, Bingyi Kang, Zilong Huang, Zhen Zhao, Xiaogang Xu, Jiashi Feng, Hengshuang Zhao.

Source:  https://huggingface.co/depth-anything/Depth-Anything-V2-Large/resolve/main/depth_anything_v2_vitl.pth
Project: https://github.com/DepthAnything/Depth-Anything-V2
Licence: CC-BY-NC-4.0 (full text in the LICENSE file beside this one)