Gy920 / segment-anything-2-real-timeLinks
Run Segment Anything Model 2 on a live video stream
☆517Updated 4 months 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☆119Updated last year
- Muggled SAM: Segmentation without the magic☆164Updated last month
- Efficient Track Anything☆640Updated 9 months ago
- Official Pytorch Implementation for “DINO-Tracker: Taming DINO for Self-Supervised Point Tracking in a Single Video” (ECCV 2024)☆520Updated 10 months ago
- [CVPR2024] Code for "SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimation".☆591Updated last year
- DINO-X: The World's Top-Performing Vision Model for Open-World Object Detection and Understanding☆1,234Updated 2 months ago
- The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2) in real-time.☆50Updated 9 months ago
- Official Implementation of CVPR24 highlight paper: Matching Anything by Segmenting Anything☆1,345Updated 5 months ago
- ☆33Updated last month
- [CVPR 2025] "A Distractor-Aware Memory for Visual Object Tracking with SAM2"☆416Updated last week
- A distilled Segment Anything (SAM) model capable of running real-time with NVIDIA TensorRT☆800Updated last year
- [ICCV 2023] Tracking Anything with Decoupled Video Segmentation☆1,433Updated 5 months ago
- Grounding DINO 1.5: IDEA Research's Most Capable Open-World Object Detection Model Series☆1,040Updated 8 months ago
- ☆387Updated last year
- [CVPR 2024 Highlight] FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects☆2,487Updated 7 months ago
- [CVPR 2025] Official PyTorch implementation of "EdgeTAM: On-Device Track Anything Model"☆602Updated 5 months ago
- [CVPR 2025 Best Paper Nomination] FoundationStereo: Zero-Shot Stereo Matching☆2,126Updated last month
- [ECCV 2024 & NeurIPS 2024] Official implementation of the paper TAPTR & TAPTRv2 & TAPTRv3☆266Updated 9 months ago
- Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2☆2,854Updated 3 weeks ago
- [CVPR 2024 Highlight] Putting the Object Back Into Video Object Segmentation☆959Updated 11 months ago
- 3D object detection using YOLO and depth estimation☆318Updated 6 months ago
- [CVPR 2025 Highlight] Video Depth Anything: Consistent Depth Estimation for Super-Long Videos☆1,449Updated this week
- The repo for "Distill Any Depth: Distillation Creates a Stronger Monocular Depth Estimator"☆644Updated 5 months ago
- [CVPR 2025] Prompt Depth Anything☆923Updated last month
- [ICCV 2023 R6D] PyTorch implementation of CNOS: A Strong Baseline for CAD-based Novel Object Segmentation based on Segmenting Anything an…☆286Updated last month
- A project that optimizes OWL-ViT for real-time inference with NVIDIA TensorRT.☆368Updated 8 months ago
- Det-Model offer bbox as conditional prompt in SAM2 video predictor Pipeline☆49Updated 9 months ago
- Official repository for "AM-RADIO: Reduce All Domains Into One"☆1,351Updated 2 weeks ago
- [CVPR 2025] RollingDepth: Video Depth without Video Models☆578Updated 6 months ago
- Official code of "EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model"☆474Updated 6 months ago