Depth-Anything
Depth-Anything copied to clipboard
[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation
Hi, I really love the work, can I deploy this work on openxlab?
Trying to run inference in MacOS yields xformer errors of not supported operations (e.g. smaller, cutlassF, tritonflashattF, etc.) Can you add support to running in MacOS (and preferable on Apple...
How can we retrieve the scale factor with the depth map? E.g., how can I obtain relative distances either in real-world units (cm, mm) or relative to pixels (depth difference...
`RuntimeError: Error(s) in loading state_dict for ZoeDepth` when running `metric_depth/evaluate.py`
THX for your great work. There is a issue when running `python metric_depth/evaluate.py -m zoedepth --pretrained_resouce "local::../checkpoints_metric_depth/depth_anything_metric_depth_outdoor.pt" -d kitti`. Since the server is not conneted to the Internet, I've downloaded...
Hi! Great work!!! very usefull. One question: is it possible that I have different results in the same image on several occasions? maybe because the interpolation or resize method in...
Thanks for your excellent and outstanding efforts in this work! Really love the work. As for `the transferring performance` experiments in Table 6, I have some questions about the detailed...
how load model form local host?
Hi @LiheYoung , Great work on `Depth-Anything`! This pull request makes it possible to run `Depth-Anything` on Replicate (https://replicate.com/cjwbw/Depth-Anything) and via API (https://replicate.com/cjwbw/Depth-Anything/api). Also happy to transfer the demo page...
Would GeForce 4090 be able to run this in real-time?
hi, thanks for your great work. I run the `run.py` on my custom images, and I'm having difficulty when using intrinsics and inferred depth map to recover point cloud. The...