Robert McCraith

[Robert McCraith @robmccr]

Can we detect cars in 3D without 3D labels?

We present a method for converting pre-trained 2D mask predictions to 3D Object Detections without any supervision on the target dataset.

Paper: https://t.co/lmElSP9ac0
Code: https://t.co/Pi01oWqWRw

[Robert McCraith @robmccr]

Added more models to MIMM (MLX Image Models)

Now includes classification (Alexnet, VGG, Resnet, Mobilenetv3, ViT) and detection (DETR)

Includes code to convert PyTorch weights and example training + validation
https://t.co/3rR2tHeMh9

[Robert McCraith @robmccr]

To be presented at @ieee_ras_icra session on Computer Vision for Transportation at 16:30 today

[Robert McCraith @robmccr]

Can we detect cars in 3D without 3D labels?

We present a method for converting pre-trained 2D mask predictions to 3D Object Detections without any supervision on the target dataset.

Paper: https://t.co/lmElSP9ac0
Code: https://t.co/Pi01oWqWRw