Detection Results using BEVFusion of Table I? about magicdrive HOT 6 CLOSED

In Table 1, we use all perception models only for testing. Therefore, we adopt the officially released ckpts without training.

from magicdrive.

Thanks for your reply!

Since the officially released ckpt of BEVFusion is in resolution of (256,704), and you resized the synthesis image (both (224,400) and (272,736)) into (256,704) resolution for evaluation?

from magicdrive.

Yes, we kept the original data processing pipeline. Actually, we upscale and pad each generated images to 1600x900 and save them to disk, so that we can run the original code without any change.

from magicdrive.

Thanks for your quick reply!

from magicdrive.

Yes, we kept the original data processing pipeline. Actually, we upscale and pad each generated images to 1600x900 and save them to disk, so that we can run the original code without any change.

Thanks for your reply!

May I ask if you could explain the specific operation of pads and upsamples here?

from magicdrive.

Hi, nice work!

Do the results of Table I all use the checkpoint officially released by bevfusion? Or the checkpoint is trained by urself?

Looking forward to your reply.

May I ask how you generate a new test set to inference BEVfusion?

from magicdrive.