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.
☆2,854Updated 8 months ago
Alternatives and similar repositories for Segment-and-Track-Anything:
Users that are interested in Segment-and-Track-Anything are comparing it to the libraries listed below
- [ECCV 2024] Official implementation of the paper "Semantic-SAM: Segment and Recognize Anything at Any Granularity"☆2,446Updated 5 months ago
- [NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"☆4,453Updated 4 months ago
- Segment Anything in High Quality [NeurIPS 2023]☆3,774Updated last month
- [ICCV 2023] Tracking Anything with Decoupled Video Segmentation☆1,302Updated 5 months ago
- Personalize Segment Anything Model (SAM) with 1 shot in 10 seconds☆1,548Updated 5 months ago
- Automated dense category annotation engine that serves as the initial semantic labeling for the Segment Anything dataset (SA-1B).☆2,177Updated last year
- Painter & SegGPT Series: Vision Foundation Models from BAAI☆2,541Updated last month
- [ECCV 2022] XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model☆1,798Updated 2 months ago
- ☆2,171Updated 7 months ago
- SAM-PT: Extending SAM to zero-shot video segmentation with point-based tracking.☆981Updated 11 months ago
- Tracking and collecting papers/projects/others related to Segment Anything.☆1,570Updated 5 months ago
- SAM with text prompt☆1,882Updated last month
- [CVPR 2023] OneFormer: One Transformer to Rule Universal Image Segmentation☆1,549Updated 3 months ago
- MetaSeg: Packaged version of the Segment Anything repository☆963Updated this week
- Segment-Anything + 3D. Let's lift anything to 3D.☆1,572Updated last year
- General AI methods for Anything: AnyObject, AnyGeneration, AnyModel, AnyTask, AnyX☆1,747Updated last year
- Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI…☆6,583Updated 7 months ago
- Caption-Anything is a versatile tool combining image segmentation, visual captioning, and ChatGPT, generating tailored captions with dive…☆1,703Updated last year
- [ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"☆7,197Updated 5 months ago
- This is the official code for MobileSAM project that makes SAM lightweight for mobile applications and beyond!☆4,945Updated last month
- EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything☆2,237Updated 3 weeks ago
- Open-source and strong foundation image recognition models.☆3,026Updated 5 months ago
- Official PyTorch implementation of "EdgeSAM: Prompt-In-the-Loop Distillation for On-Device Deployment of SAM"☆937Updated 5 months ago
- Segment Anything Labelling Tool☆1,028Updated 10 months ago
- [CVPR 2024 Highlight] Putting the Object Back Into Video Object Segmentation☆776Updated 2 months ago
- Project Page for "LISA: Reasoning Segmentation via Large Language Model"☆1,949Updated 2 weeks ago
- [CVPR 2023] Official implementation of the paper "Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segme…☆1,250Updated last year
- Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2☆1,518Updated 3 weeks ago
- Adapting Meta AI's Segment Anything to Downstream Tasks with Adapters and Prompts☆1,101Updated 3 weeks ago
- Official Implementation of CVPR24 highligt paper: Matching Anything by Segmenting Anything☆1,152Updated 2 months ago