Downloads · 30 days
8
25% of all-time downloads
ACR-cuboid-v1.1.1
cmes-deepvision/ACR-cuboid-v1.1.1
ACR-cuboid-v1.1.1 is a robotics model from cmes-deepvision. Use it for the robotics task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Single-class (carton box) 3D cuboid pose estimation model for ACR robotic picking.
All-time downloads
32
Public
Parameters
122M
490 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors490 MB · 100%
At a glance
- Task
- Robotics
- License
- apache-2.0
- Model type
- deformable_detr
- Access
- Public
- Created
- Jul 13, 2026
- Updated
- Jul 13, 2026
- SHA
- ecd9f66d
Model card
From the Hugging Face model README
ACR-cuboid-v1.1.1
Single-class (carton box) 3D cuboid pose estimation model for ACR robotic picking.
Changes from v1.1.0
- Bugfix: Fixed 3 geometric augmentation bugs in
rgbd_transforms.py:RandomRotation90RGBD: k=1 / k=3 center_2d and box label formulas were swappedRandomRotateRGBD: box width/height not updated after rotationMultiCropRGBD: stale labels returned when no objects survive crop
- Retrained 30 epochs with full geometric augmentation pipeline (v1.1.0 used paper-only augmentation)
Eval (checkpoint-2100, epoch 30)
| Metric | Val | Test |
|---|---|---|
| 3D IoU [email protected] | 99.97% | 100.0% |
| 3D IoU [email protected] | 94.85% | 93.46% |
| COCO 2D AP | 99.76% | 99.45% |
| F1 (score≥0.5) | 99.65% | 99.83% |
| Translation (median) | 10.28mm | 10.33mm |
| Rotation (median) | 1.41° | 1.24° |
| Size LWH (median) | 12.53mm | 12.34mm |
Architecture
OpenVocabCuboidMapAnythingDINOFor3DObjectDetection- Backbone: DINOv2-S (384-dim, 12 layers, registers)
- Decoder: 9-layer deformable DETR
- Parameters: 122.4M
- Input: 1280×1280
Compatibility
Drop-in replacement for v1.1.0 — identical config, architecture, and weight keys.
- Task
- Robotics
- Type
- deformable_detr
- License
- apache-2.0
- Created
- Jul 13, 2026
- Updated
- Jul 13, 2026