search

Yzichen / FlashOCC

260 stars 28 forks source link

Regarding acceleration in evaluating FPS #71

Open cdb342 opened 3 days ago

cdb342 commented 3 days ago

img_v3_02ff_de20efd9-fbb1-4c4e-ba7f-20981a2f47cg It appears that acceleration is used when evaluating FPS, which assumes fixed camera extrinsics and intrinsics for each sample. However, in the NuScenes dataset, camera parameters change even between frames. I suspect the appropriateness of making this assumption when measuring FPS, especially since other works don't seem to make this assumption.

Yzichen commented 2 days ago

In fact, we make this assumption following bevdet. Moreover, we believe that in practice, the extrinsics and intrinsics are fixed, so this assumption is reasonable, despite the performance degradation for nuscenes.

cdb342 commented 14 hours ago

In fact, we make this assumption following bevdet. Moreover, we believe that in practice, the extrinsics and intrinsics are fixed, so this assumption is reasonable, despite the performance degradation for nuscenes.

Thanks for your response. Do you know why the camera parameters change between frames in nuscenes. Are they calibrated frame by frame?