IDEA-Research / Grounded-SAM-2
Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2
☆2,013Updated this week
Alternatives and similar repositories for Grounded-SAM-2:
Users that are interested in Grounded-SAM-2 are comparing it to the libraries listed below
- SAM with text prompt☆2,113Updated this week
- Grounding DINO 1.5: IDEA Research's Most Capable Open-World Object Detection Model Series☆934Updated 3 months ago
- DINO-X: The World's Top-Performing Vision Model for Open-World Object Detection and Understanding☆1,005Updated this week
- [ECCV 2024] Official implementation of the paper "Semantic-SAM: Segment and Recognize Anything at Any Granularity"☆2,590Updated 9 months ago
- Official Implementation of CVPR24 highlight paper: Matching Anything by Segmenting Anything☆1,265Updated 5 months ago
- [ICCV 2023] Tracking Anything with Decoupled Video Segmentation☆1,364Updated 8 months ago
- EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything☆2,320Updated 4 months ago
- [ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"☆7,910Updated 8 months ago
- Automated dense category annotation engine that serves as the initial semantic labeling for the Segment Anything dataset (SA-1B).☆2,230Updated last year
- Fine-tune SAM (Segment Anything Model) for computer vision tasks such as semantic segmentation, matting, detection ... in specific scena…☆827Updated last year
- Segment Anything in High Quality [NeurIPS 2023]☆3,886Updated 4 months ago
- Official code for "FeatUp: A Model-Agnostic Frameworkfor Features at Any Resolution" ICLR 2024☆1,491Updated 9 months ago
- Official repository for "AM-RADIO: Reduce All Domains Into One"☆1,117Updated last week
- Tracking and collecting papers/projects/others related to Segment Anything.☆1,610Updated last month
- This is the third party implementation of the paper Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectio…☆582Updated 10 months ago
- YOLOE: Real-Time Seeing Anything☆1,155Updated 3 weeks ago
- Personalize Segment Anything Model (SAM) with 1 shot in 10 seconds☆1,574Updated 9 months ago
- Open-source and strong foundation image recognition models.☆3,180Updated 2 months ago
- An open-source project dedicated to tracking and segmenting any objects in videos, either automatically or interactively. The primary alg…☆2,935Updated last year
- Fine-tune Segment-Anything Model with Lightning Fabric.☆535Updated last year
- [CVPR 2024] Official implementation of the paper "Visual In-context Learning"☆463Updated last year
- Run Segment Anything Model 2 on a live video stream☆355Updated 3 months ago
- A distilled Segment Anything (SAM) model capable of running real-time with NVIDIA TensorRT☆746Updated last year
- [ECCV2024] API code for T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergy☆2,460Updated this week
- Official PyTorch implementation of "EdgeSAM: Prompt-In-the-Loop Distillation for On-Device Deployment of SAM"☆1,000Updated 8 months ago
- This is the official PyTorch implementation of the paper Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP.☆721Updated last year
- [CVPR 2023] OneFormer: One Transformer to Rule Universal Image Segmentation☆1,592Updated 6 months ago
- [ICCV 2023] Official implementation of the paper "A Simple Framework for Open-Vocabulary Segmentation and Detection"☆704Updated last year
- MetaSeg: Packaged version of the Segment Anything repository☆976Updated this week
- [NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"☆4,565Updated 8 months ago