Gy920 / segment-anything-2-real-timeLinks
Run Segment Anything Model 2 on a live video stream
☆436Updated 3 weeks ago
Alternatives and similar repositories for segment-anything-2-real-time
Users that are interested in segment-anything-2-real-time are comparing it to the libraries listed below
Sorting:
- Grounded Tracking for Streaming Videos☆104Updated 8 months ago
- DINO-X: The World's Top-Performing Vision Model for Open-World Object Detection and Understanding☆1,096Updated last week
- Muggled SAM: Segmentation without the magic☆143Updated 2 months ago
- Official Pytorch Implementation for “DINO-Tracker: Taming DINO for Self-Supervised Point Tracking in a Single Video” (ECCV 2024)☆491Updated 7 months ago
- Efficient Track Anything☆571Updated 5 months ago
- [CVPR 2025] "A Distractor-Aware Memory for Visual Object Tracking with SAM2"☆329Updated last month
- Official Implementation of CVPR24 highlight paper: Matching Anything by Segmenting Anything☆1,305Updated last month
- Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2☆2,347Updated last month
- [CVPR2024] Code for "SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimation".☆532Updated 11 months ago
- The repo for "Distill Any Depth: Distillation Creates a Stronger Monocular Depth Estimator"☆599Updated 2 months ago
- ☆24Updated last month
- [CVPR 2025 Highlight] Video Depth Anything: Consistent Depth Estimation for Super-Long Videos☆1,097Updated this week
- [ECCV 2024 & NeurIPS 2024] Official implementation of the paper TAPTR & TAPTRv2 & TAPTRv3☆265Updated 6 months ago
- [CVPR 2024 Highlight] Official PyTorch implementation of SpatialTracker: Tracking Any 2D Pixels in 3D Space☆875Updated last month
- [CVPR 2025 Best Paper Nomination] FoundationStereo: Zero-Shot Stereo Matching☆1,768Updated last week
- A distilled Segment Anything (SAM) model capable of running real-time with NVIDIA TensorRT☆765Updated last year
- A Graph-Based Approach for Category-Agnostic Pose Estimation [ECCV 2024]☆366Updated 6 months ago
- Official code of "EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model"☆423Updated 3 months ago
- WiLoR: End-to-end 3D hand localization and reconstruction in-the-wild☆320Updated last week
- Grounding DINO 1.5: IDEA Research's Most Capable Open-World Object Detection Model Series☆972Updated 5 months ago
- [CVPR 2025] RollingDepth: Video Depth without Video Models☆546Updated 3 months ago
- [CVPR 2024 Highlight] Putting the Object Back Into Video Object Segmentation☆892Updated 7 months ago
- [CVPR 2025] Prompt Depth Anything☆843Updated 3 months ago
- Python scripts for the Segment Anythin 2 (SAM2) model in ONNX☆251Updated 9 months ago
- Official repository for "AM-RADIO: Reduce All Domains Into One"☆1,223Updated this week
- TensorRT implementation of Depth-Anything V1, V2☆384Updated 3 months ago
- Code for "MatchAnything: Universal Cross-Modality Image Matching with Large-Scale Pre-Training", Arxiv 2025.☆942Updated 5 months ago
- The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2) in real-time.☆36Updated 6 months ago
- [ICCV 2023 R6D] PyTorch implementation of CNOS: A Strong Baseline for CAD-based Novel Object Segmentation based on Segmenting Anything an…☆264Updated 5 months ago
- [CVPR 2024 Highlight] FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects☆2,195Updated 3 months ago