Alternatives and similar repositories for SAM2_streaming

Users that are interested in SAM2_streaming are comparing it to the libraries listed below

• Gy920 / segment-anything-2-real-time
  Run Segment Anything Model 2 on a live video stream
  ☆500Updated 3 months ago
• IDEA-Research / DINO-X-API
  DINO-X: The World's Top-Performing Vision Model for Open-World Object Detection and Understanding
  ☆1,210Updated last month
• zdata-inc / sam2_realtime
  The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2) in real-time.
  ☆46Updated 9 months ago
• azimjaan21 / jetpack-6.1-pytorch-torchvision-
  🚀 Installing PyTorch and Building TorchVision on JetPack 6.1 For NVIDIA Jetson Orin AGX Developer Kit
  ☆37Updated 9 months ago
• hkchengrex / Cutie
  [CVPR 2024 Highlight] Putting the Object Back Into Video Object Segmentation
  ☆942Updated 10 months ago
• NVIDIA-AI-IOT / nanosam
  A distilled Segment Anything (SAM) model capable of running real-time with NVIDIA TensorRT
  ☆798Updated last year
• robrosinc / REALTIME_SAM2
  ☆33Updated last month
• patrick-tssn / Streaming-Grounded-SAM-2
  Grounded Tracking for Streaming Videos
  ☆119Updated 11 months ago
• NVIDIA-AI-IOT / nanoowl
  A project that optimizes OWL-ViT for real-time inference with NVIDIA TensorRT.
  ☆367Updated 7 months ago
• ibaiGorordo / ONNX-SAM2-Segment-Anything
  Python scripts for the Segment Anythin 2 (SAM2) model in ONNX
  ☆264Updated last year
• niconielsen32 / YOLO-3D
  3D object detection using YOLO and depth estimation
  ☆298Updated 6 months ago
• jovanavidenovic / DAM4SAM
  [CVPR 2025] "A Distractor-Aware Memory for Visual Object Tracking with SAM2"
  ☆384Updated 2 months ago
• yformer / EfficientTAM
  Efficient Track Anything
  ☆629Updated 8 months ago
• THU-MIG / yoloe
  YOLOE: Real-Time Seeing Anything [ICCV 2025]
  ☆1,746Updated 2 months ago
• JiehongLin / SAM-6D
  [CVPR2024] Code for "SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimation".
  ☆581Updated last year
• fabio-sim / Depth-Anything-ONNX
  ONNX-compatible Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data
  ☆379Updated 11 months ago
• heyoeyo / muggled_sam
  Muggled SAM: Segmentation without the magic
  ☆159Updated last week
• NVIDIA-ISAAC-ROS / isaac_ros_pose_estimation
  Deep learned, NVIDIA-accelerated 3D object pose estimation
  ☆335Updated last month
• Aimol-l / SAM2Export
  try to export sam2 to onnx.
  ☆71Updated 4 months ago
• yuvraj108c / ml-depth-pro-tensorrt
  Experimental TensorRT implementation of apple ml-depth-pro for faster inference
  ☆21Updated 11 months ago
• axinc-ai / segment-anything-2
  The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained mode…
  ☆67Updated 3 months ago
• alaamaalouf / FollowAnything
  ☆385Updated last year
• ammar-n-abbas / FoundationPoseROS2
  FoundationPoseROS2 is a ROS2-integrated system for 6D object pose estimation and tracking, based on the FoundationPose architecture. It u…
  ☆178Updated 3 months ago
• AssafSinger94 / dino-tracker
  Official Pytorch Implementation for “DINO-Tracker: Taming DINO for Self-Supervised Point Tracking in a Single Video” (ECCV 2024)
  ☆512Updated 9 months ago
• IRVLUTD / NIDS-Net
  [IROS 2025] NIDS-Net: A unified framework for novel instance detection and segmentation
  ☆67Updated 4 months ago
• lyxlplhy / Sam2-collection
  ☆14Updated 5 months ago
• zhujiajian98 / Depth-Anythingv2-TensorRT-python
  Transform the depth-anything-v2 model to tensorrt.
  ☆28Updated this week
• motern88 / Det-SAM2
  Det-Model offer bbox as conditional prompt in SAM2 video predictor Pipeline
  ☆49Updated 8 months ago
• Kaivalya192 / live-pose
  Intel realsense Depth camera compitable python package for 6 DOF pose estimation
  ☆41Updated 5 months ago
• mgonzs13 / yolo_ros
  Ultralytics YOLOv8, YOLOv9, YOLOv10, YOLOv11, YOLOv12 for ROS 2
  ☆808Updated 3 weeks ago