PatchFusion
PatchFusion copied to clipboard
zhyever
[CVPR 2024] An End-to-End Tile-Based Framework for High-Resolution Monocular Metric Depth Estimation
`AttributeError: 'dict' object has no attribute 'pretrained_resource' `occurred when I executed `model = PatchFusion.from_pretrained(model_name).to(DEVICE).eval() ` It looks like the dictionary is accessed through dots. Any suggestions on how to deal...
Since metric depth estimation means that the depth of the sky will not be realistic, is it possible to train Patchfusion for relative depth estimation to solve the sky issue?
Will it be possible to use Marigold Depth Estimation along with PatchFusion? Also I was wondering if you could compare both models side-by-side.
Due to the GPU memory limit, I was only able to test the project on "depthanything_s" and "b" models. However, I noticed the presence of ghost artifacts, especially in the...
1. Can I know the setting for getting the same quantitative result with the paper? 2. Do you have a plan to provide the patchfusion network trained with MVS-Synth? or...
Hi @zhyever , I recently tried out patchfusion model using this repo. Currently I'm trying to run the training script to train a model by myself. Following the training steps...
The steps using conda say to use "export" command, which is not recognized.. we apparently have to use "set" instead.. and later, the "from" command, which also isn't recognized or...
Hi, sir. Thanks for great work and opened source for sharing. I'm also looking into monocular depth estimation and have a question about tile-based depth estimation approach. In section 3.1.(iii),...
