Use Grounding DINO, Segment Anything, and GPT-4V to label images with segmentation masks for use in training smaller, fine-tuned models.
MIT License
Edit anything in images powered by segment-anything, ControlNet, StableDiffusion, etc. (ACM MM)
[ICCV 2023] Tracking Anything with Decoupled Video Segmentation
Implementation of Segnet, FCN, UNet , PSPNet and other models in Keras.
EfficientViT is a new family of vision models for efficient high-resolution vision.
[ECCV 2024] Official implementation of the paper "Semantic-SAM: Segment and Recognize Anything at...
Automated dense category annotation engine that serves as the initial semantic labeling for the S...
The Most Faithful Implementation of Segment Anything (SAM) in 3D
A Python package for segmenting geospatial data with the Segment Anything Model (SAM)
Segment Anything in High Quality [NeurIPS 2023]
Personalize Segment Anything Model (SAM) with 1 shot in 10 seconds
A simple demo for SAM+MMDetection
Export Segment Anything Models to ONNX
A central hub for gathering and showcasing amazing projects that extend OpenMMLab with SAM and ot...
Use Grounding DINO, Segment Anything, and CLIP to label objects in images.
[CVPR2024 Highlight]GLEE: General Object Foundation Model for Images and Videos at Scale