… we have addressed the 2D/3D object detection problem by introducing the IoU loss for two …
IoU loss layer which can be directly applied for axis-aligned or rotated 2D/3D object detection …

… the DIoU loss [40] for 2D object detection to take our RDIoU for 3D object detection with …
show RDIoU-guided DIoU loss can surpass the 3D IoU-guided DIoU loss by a large margin. …

… differences between IoU losses and distance loss is that IoU considers all … However, IoU loss
in 3D object detection brings additional … IIoU loss has two portions: IoU loss and center loss. …

… the IoU loss in the axis-aligned 2D object detection which is invariant to the scale, our method
jointly optimizes the parameters via the \(\textit{RIoU}\) loss. … an IoU for 3D object detection …

… loss disentanglement significantly improves losses on both, 2D and 3D tasks. It also enables
us to effectively train the entire CNN architecture (2D+3D… study the signed IoU loss function (…

… an IoU oriented loss for 3D size estimation. The new IoU oriented loss dynamically adjust the
loss … Then, we recover 2D/3D bounding boxes according to encoding strategy introduced in …

… 3D object detection, we propose an IoU guided network that aims at perceiving a more
accurate IoU as the detection … Yang, “IoU loss for 2D/3D object detection,” in 2019 International …

… designed orientation-decoupled IoU regression loss along with the IoU-aware prediction …
, and then capitalize on 2D/3D CNN to perform 3D object detection. The pioneering VoxelNet […

… the 3D IoU between the 3D proposals and the object solely … because of the ambiguities
arising from 2D-3D mapping. Many … For the 3D IoU regression, we use the smooth L1 loss, since …

… To solve suboptimal regression of 3D IoU loss for objects at different … Finally, we integrate
GCIoU Loss into multiple models to … Iou loss for 2d/3d object detection. In 2019 International …