diff --git a/.asset/COCO.png b/.asset/COCO.png new file mode 100644 index 0000000..9e80d1a Binary files /dev/null and b/.asset/COCO.png differ diff --git a/.asset/GD_GLIGEN.png b/.asset/GD_GLIGEN.png new file mode 100644 index 0000000..85f0be4 Binary files /dev/null and b/.asset/GD_GLIGEN.png differ diff --git a/.asset/GD_SD.png b/.asset/GD_SD.png new file mode 100644 index 0000000..6288a36 Binary files /dev/null and b/.asset/GD_SD.png differ diff --git a/.asset/ODinW.png b/.asset/ODinW.png new file mode 100644 index 0000000..8242ab1 Binary files /dev/null and b/.asset/ODinW.png differ diff --git a/README.md b/README.md index e358466..281f9b0 100644 --- a/README.md +++ b/README.md @@ -8,13 +8,43 @@ Official pytorch implementation of [Grounding DINO](https://arxiv.org/abs/2303.05499). Code will be available soon! ## Highlight -- SOTA Closed-Set Detection Model [DINO](https://github.com/IDEA-Research/DINO) => SOTA Open-Set Detection Model **Grounding DINO** -- Pure Transformer-based. -- COCO zero-shot **52.5 AP** (training without COCO data!). COCO fine-tune **63.0 AP**. +- **Open-Set Detection.** Detect **everything** with language! +- **High Performancce.** COCO zero-shot **52.5 AP** (training without COCO data!). COCO fine-tune **63.0 AP**. +- **Flexible.** Collaboration with Stable Diffusion for Image Editting. ![hero_figure](.asset/hero_figure.png) +## Results +
+ +COCO Object Detection Results + +COCO +
+ +
+ +ODinW Object Detection Results + +ODinW +
+ +
+ +Marrying Grounding DINO with Stable Diffusion for Image Editing + +GD_SD +
+ +
+ +Marrying Grounding DINO with GLIGEN for more Detailed Image Editing + +GD_GLIGEN +
+ + ## Model Includes: a text backbone, an image backbone, a feature enhancer, a language-guided query selection, and a cross-modality decoder. @@ -27,6 +57,8 @@ Our model is related to [DINO](https://github.com/IDEA-Research/DINO) and [GLIP] We also thank great previous work including DETR, Deformable DETR, SMCA, Conditional DETR, Anchor DETR, Dynamic DETR, DAB-DETR, DN-DETR, etc. More related work are available at [Awesome Detection Transformer](https://github.com/IDEACVR/awesome-detection-transformer). A new toolbox [detrex](https://github.com/IDEA-Research/detrex) is available as well. +Thanks [Stable Diffusion](https://github.com/Stability-AI/StableDiffusion) and [GLIGEN](https://github.com/gligen/GLIGEN) for their awesome models. + # Bibtex If you find our work helpful for your research, please consider citing the following BibTeX entry.