[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"
- object-detection
- open-world
- open-world-detection
- vision-language
Repository Index
72,362 visible repositories in the index
1–4 of 4 · Most stars
[NeurIPS 2025] SpatialLM: Training Large Language Models for Structured Indoor Modeling
- scene-understanding
- spatial-intelligence
- mllm
- point-clouds
SAM with text prompt
VLX-Seek is an efficient VLM that grounds fine-grained visual targets with high precision in wild environments.
- object-detection
- open-vocabulary-detection
- vision-and-language
- visual-grounding