Visualization of v1 and v2 model

[Terencedu]

Hi, thank you for your great work! I have some questions of visualization of v1 and v2 model.

Config (v1 model): M3:FlashOCC-4D-Stereo (2f):

1. Why are there two vertical bars of blank space next to the ego car in many pictures?

Config (v2 model): FlashOCCV2-4DLongterm-Depth (16f):

1. Why is the ground plane basically blank？
2. This v2 model did not use camera mask for training. I think it can improve the prediction of invisible area like far sky compared to v1 model, but why does the v2 model predict both the sky and the ground poorly and which part improves in v2 model?

Hope to get your answer, thank you！

[Yzichen]

That's odd, I'll take some time to check it out when I'm not busy recently .

[Yzichen]

https://github.com/Yzichen/FlashOCC/blob/d1a41bc5fd99b290cb7f0d1642296c02cb7c58c3/tools/analysis_tools/vis_occ.py#L336-L340

The problem seems to be on voxel_show, which is now using the camera mask, so there's a lot of blank space in the invisible area. You can try without it.

when voxel_show = np.logical_and(pred_occ != FREE_LABEL, camera_mask):

when voxel_show = pred_occ != FREE_LABEL:

[upupbo]

step 1. generate result bash tools/dist_test.sh projects/configs/flashocc/flashocc-r50.py ckpts/flashocc-r50-256x704.pth 4 --eval map --eval-options show_dir=work_dirs/flashocc_r50/results

step 2. visualization python tools/analysis_tools/vis_occ.py work_dirs/flashocc_r50/results/ --root_path ./data/nuscenes --save_path ./vis An error occurs when running the second step： vis: VisualizerWithKeyCallback with name Open3D view_control: None Traceback (most recent call last): File "tools/analysis_tools/vis_occ.py", line 420, in main() File "tools/analysis_tools/vis_occ.py", line 359, in main view_control.set_lookat(look_at) AttributeError: 'NoneType' object has no attribute 'set_lookat'