SurroundDepth
SurroundDepth copied to clipboard
How to get the metric depth?
Dear author: Thank you very much for your contributions in this paper! I try to get the depth in evaluation. Theoretically, we can get the metric depth between min_depth and max_depth(meter) after the function 'disp_to_depth' . However, I observed several groups of depth generated in this way, it seems not like a correct metric depth. As below: (Pdb) pred_depth array([[0.7076706 , 0.7073359 , 0.70599675, ..., 0.60197115, 0.59946537, 0.5988389 ], [0.70776784, 0.7074405 , 0.7061312 , ..., 0.60220945, 0.599669 , 0.59903383], [0.7082062 , 0.70791256, 0.706738 , ..., 0.603285 , 0.60058796, 0.5999137 ], ..., [0.11618532, 0.1162222 , 0.11636975, ..., 0.11287601, 0.11278087, 0.11275709], [0.11617843, 0.11621682, 0.11637037, ..., 0.11286871, 0.11277094, 0.11274651], [0.1161769 , 0.11621563, 0.11637051, ..., 0.11286709, 0.11276875, 0.11274416]], dtype=float32) The depth number is very small compare to real depth, much of them less than 1.0. So how to get the metric depth?
Hi, which model do you use? For the scale-ambiguous model, it cannot predict real-world scale. However, for the scale-aware model, it is able to predict real depth.
Hi,why scale-aware model's Abs Real is larger than acale-ambiguous in nuScenes dataset?
For scale-ambiguous experiments, we conduct median-scaling during evaluation. If scale-aware depths are absolutely accurate, the scale-aware results should be equal to scale-ambiguious results. However, currently scale-aware depths have errors and median-scaling will boost the quantitative results.
Thank for your help!