I am experimenting with using DepthAnything for depth supervision (not inverse depth == disparity). I am wondering if you have any advice in converting disparity estimates to relative depths, because I have some doubts. I tried something simple like depth = 1 / output_disparity.clamp(min=0.01) but I have some doubts because I get quite different looking depth maps compared to Zoe Depth on some of the indoor datasets I am playing with:
Inverse of DepthAnything:
Zoe depth output:
Let me know if you have any recommendations. Thanks.
Hi
I am experimenting with using DepthAnything for depth supervision (not inverse depth == disparity). I am wondering if you have any advice in converting disparity estimates to relative depths, because I have some doubts. I tried something simple like
depth = 1 / output_disparity.clamp(min=0.01)
but I have some doubts because I get quite different looking depth maps compared to Zoe Depth on some of the indoor datasets I am playing with:Inverse of DepthAnything:
Zoe depth output:
Let me know if you have any recommendations. Thanks.