Gy920 / segment-anything-2-real-time
Run Segment Anything Model 2 on a live video stream
☆183Updated last month
Related projects ⓘ
Alternatives and complementary repositories for segment-anything-2-real-time
- Grounded Tracking for Streaming Videos☆48Updated last month
- Official Pytorch Implementation for “DINO-Tracker: Taming DINO for Self-Supervised Point Tracking in a Single Video”☆417Updated 4 months ago
- [ACCV 2024 (Oral)] Official Implementation of "Moving Object Segmentation: All You Need Is SAM (and Flow)" Junyu Xie, Charig Yang, Weidi …☆273Updated 3 weeks ago
- [ECCV 2024] Official implementation of the paper "TAPTR: Tracking Any Point with Transformers as Detection"☆200Updated 3 months ago
- [CVPR2024] Code for "SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimation".☆360Updated 4 months ago
- ☆211Updated 4 months ago
- TensorRT implementation of Depth-Anything V1, V2☆291Updated last month
- Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2☆1,141Updated 2 weeks ago
- [ICCV 2023 R6D] PyTorch implementation of CNOS: A Strong Baseline for CAD-based Novel Object Segmentation based on Segmenting Anything an…☆213Updated last month
- Muggled SAM: Segmentation without the magic☆58Updated last week
- Depth Any Video with Scalable Synthetic Data☆398Updated 3 weeks ago
- A Graph-Based Approach for Category-Agnostic Pose Estimation [ECCV 2024]☆320Updated 3 weeks ago
- Python scripts for the Segment Anythin 2 (SAM2) model in ONNX☆175Updated 2 months ago
- A distilled Segment Anything (SAM) model capable of running real-time with NVIDIA TensorRT☆664Updated last year
- Official Code for Tracking Any Object Amodally☆113Updated 4 months ago
- Universal Monocular Metric Depth Estimation☆626Updated last month
- ☆363Updated 11 months ago
- ☆144Updated 5 months ago
- Pytorch Implementation of "SMITE: Segment Me In TimE"☆161Updated 3 weeks ago
- GeoCalib: Learning Single-image Calibration with Geometric Optimization (ECCV 2024)☆464Updated last week
- Use Segment Anything 2, grounded with Florence-2, to auto-label data for use in training vision models.☆92Updated 3 months ago
- Code release for CVPR'24 submission 'OmniGlue'☆575Updated 3 months ago
- [CVPR 2024] Official implementation of the paper "Visual In-context Learning"☆393Updated 7 months ago
- API for Grounding DINO 1.5: IDEA Research's Most Capable Open-World Object Detection Model Series☆778Updated 3 months ago
- [CVPR 2024 - Oral] Matching 2D Images in 3D: Metric Relative Pose from Metric Correspondences☆473Updated 2 months ago
- [ICCV2023] VLPart: Going Denser with Open-Vocabulary Part Segmentation☆357Updated last year
- ONNX-compatible Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data☆264Updated last month
- [CVPR 2024] RoMa: Robust Dense Feature Matching; RoMa is the robust dense feature matcher capable of estimating pixel-dense warps and rel…☆619Updated 3 weeks ago
- The repo for "Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image" and "Metric3Dv2: A Versatile Monocular Geometric Foun…☆1,428Updated 2 weeks ago
- [NeurIPS 2024] Code release for "Segment Anything without Supervision"☆420Updated last month