Grounding DINO
Open-set object detection combining DINO with grounded pre-training.
About
Grounding DINO by IDEA Research is an open-set object detector that finds objects described by free-text prompts without category-specific training, marrying the DINO detector with grounded vision-language pretraining. It reaches strong zero-shot detection scores on COCO and is commonly paired with Segment Anything for text-prompted segmentation. PyTorch code and pretrained models are provided. Released under the Apache 2.0 license.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Intermediate (3/5)
- License
- Apache-2.0
- Minimum VRAM
- 4 GB
- Added
- Apr 3, 2026
Related Tools
Simple and effective multi-object tracking using every detection box.
Monocular depth estimation model producing detailed depth maps from single images.
End-to-end object detection with transformers by Meta, eliminating hand-designed components.
Self-supervised vision transformer by Meta producing universal visual features.
Unified vision foundation model by Microsoft for captioning, detection, and segmentation.
Robust multi-object tracking combining motion and appearance cues.