
Monocular 3D detectors struggle to generalize to large objects due to the noise sensitivity of depth regression losses. SeaBird, a novel pipeline, effectively integrates BEV segmentation supervised by the noise-robust dice loss to improve monocular 3D detection of large objects.


coremsg

improving-monocular-3d-detection-of-large-objects-with-segmentation-in-bird-s-view-and-dice-loss


Improving Monocular 3D Detection of Large Objects with Segmentation in Bird's View and Dice Loss
