ewrfcas

sorry, i have missed the address.

Hi, I have also tested LoFTR but only get this result.  This is my setting:  Maybe I need to use the indoor weights?

Thanks for your reply. I have tested HPatches with the AUC of 3px:64.58, 5px:74.77, 10px:84.32. Besides, I read the LoFTR paper and find that they used LoFTR-OT, while I used...

Hi, I have tried another setting: confidence threshold=0.2, and achieve  This result is better than the previous one with a 0.5 threshold:  Any comments?

I remember that I removed the code "try...except..." for the debugging. Would it have any influence on the final results?

Anyhow, thanks for your response. I will try LoFTR-OT and response the results here.

How to get the upsacle model? This address is not useable now. https://huggingface.co/stabilityai/stable-diffusion-2-depth/resolve/main/x4-upscaler-ema.ckpt

> > How to get the upsacle model? > > This address is not useable now. > > Presumably you want this repo? > > * https://huggingface.co/stabilityai/stable-diffusion-x4-upscaler/tree/main > > With...

The same question

Why the predicted depth is not processed with 'log' (but gt depth is log) before the gradient loss?