wl-zhao / VPD

[ICCV 2023] VPD is a framework that leverages the high-level and low-level knowledge of a pre-trained text-to-image diffusion model to downstream visual perception tasks.
https://vpd.ivg-research.xyz
MIT License
514 stars 31 forks source link

Blurred depth maps #45

Open Aradhye2002 opened 1 year ago

Aradhye2002 commented 1 year ago

Hi,

I tried visualizing the depth map on one of the test images. But I am getting some blurring in the depth map:

Screenshot 2023-09-23 at 10 39 38 AM

On the other hand models like ZoeDepth produce a sharper depth map:

download

Why might this be happening?

Looking forward to your reply. Thanks

EmmaThompson123 commented 1 year ago

Hi, could you please share the code that inference on your custom image ?