z-x-yang / Segment-and-Track-Anything
An open-source project dedicated to tracking and segmenting any objects in videos, either automatically or interactively. The primary algorithms utilized include the Segment Anything Model (SAM) for key-frame segmentation and Associating Objects with Transformers (AOT) for efficient tracking and propagation purposes.
☆2,852Updated 6 months ago
Related projects ⓘ
Alternatives and complementary repositories for Segment-and-Track-Anything
- Personalize Segment Anything Model (SAM) with 1 shot in 10 seconds☆1,521Updated 3 months ago
- [ECCV 2024] Official implementation of the paper "Semantic-SAM: Segment and Recognize Anything at Any Granularity"☆2,362Updated 4 months ago
- [NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"☆4,391Updated 3 months ago
- [ICCV 2023] Tracking Anything with Decoupled Video Segmentation☆1,269Updated 3 months ago
- Caption-Anything is a versatile tool combining image segmentation, visual captioning, and ChatGPT, generating tailored captions with dive…☆1,683Updated last year
- Segment Anything in High Quality [NeurIPS 2023]☆3,713Updated this week
- Painter & SegGPT Series: Vision Foundation Models from BAAI☆2,523Updated last year
- Automated dense category annotation engine that serves as the initial semantic labeling for the Segment Anything dataset (SA-1B).☆2,152Updated last year
- Tracking and collecting papers/projects/others related to Segment Anything.☆1,546Updated 3 months ago
- MetaSeg: Packaged version of the Segment Anything repository☆957Updated this week
- [ECCV 2022] XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model☆1,773Updated this week
- SAM-PT: Extending SAM to zero-shot video segmentation with point-based tracking.☆974Updated 9 months ago
- Project Page for "LISA: Reasoning Segmentation via Large Language Model"☆1,873Updated 4 months ago
- General AI methods for Anything: AnyObject, AnyGeneration, AnyModel, AnyTask, AnyX☆1,729Updated last year
- OneFormer: One Transformer to Rule Universal Image Segmentation, arxiv 2022 / CVPR 2023☆1,505Updated last month
- Official PyTorch implementation of "EdgeSAM: Prompt-In-the-Loop Distillation for On-Device Deployment of SAM"☆940Updated 3 months ago
- [ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"☆6,768Updated 3 months ago
- ☆2,141Updated 5 months ago
- Segment-Anything + 3D. Let's lift anything to 3D.☆1,556Updated last year
- [CVPR 2024 Highlight] Putting the Object Back Into Video Object Segmentation☆731Updated last week
- Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2☆1,141Updated 2 weeks ago
- SAM with text prompt☆1,736Updated this week
- Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI…☆6,504Updated 5 months ago
- Open-source and strong foundation image recognition models.☆2,893Updated 3 months ago
- Adapting Meta AI's Segment Anything to Downstream Tasks with Adapters and Prompts☆1,053Updated 3 months ago
- Segment Anything Labelling Tool☆1,024Updated 9 months ago
- [CVPR2024 Highlight]GLEE: General Object Foundation Model for Images and Videos at Scale☆1,083Updated last month
- This is the official PyTorch implementation of the paper Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP.☆690Updated last year
- EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything☆2,160Updated 5 months ago
- This repository contains the code of the CVPR 2022 paper "Image Segmentation Using Text and Image Prompts".☆1,135Updated 10 months ago