Alternatives and similar repositories for Segment-Any-Video

Users that are interested in Segment-Any-Video are comparing it to the libraries listed below

• IDEA-Research / deepdataspace
  The Go-To Choice for CV Data Visualization, Annotation, and Model Analysis.
  ☆260Updated last year
• PaddleCV-SIG / PaddleLabel
  飞桨智能标注，让标注快人一步
  ☆293Updated last year
• mindspore-lab / mindyolo
  A toolbox of yolo models and algorithms based on MindSpore
  ☆169Updated 2 months ago
• OschAI / VisioFirm
  VisioFirm: Cross-Platform AI-assisted Annotation Tool for Computer Vision
  ☆415Updated 4 months ago
• zhouayi / SAM-Tool
  利用Segment Anything(SAM)模型进行快速标注
  ☆237Updated 4 months ago
• Asad-Ismail / Grounding-Dino-FineTuning
  Fine tuning grounding Dino
  ☆156Updated 6 months ago
• lllcho / LabelV
  视频分类标注、视频时空标注
  ☆44Updated 2 years ago
• hpc203 / GroundingDINO-onnxrun
  使用onnxruntime部署GroundingDINO开放世界目标检测，包含C++和Python两个版本的程序
  ☆82Updated 2 years ago
• open-mmlab / labelbee
  LabelBee is an annotation Library
  ☆296Updated this week
• wenyi5608 / GroundingDINO
  Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"
  ☆45Updated 2 years ago
• LSH9832 / SAMLabelerPro
  label your image with Segment Anything Model or MobileSAM, support remote labeling for multiple persons。使用Segment Anything Model或MobileSA…
  ☆86Updated last year
• iMoonLab / Hyper-YOLOv1.1
  The source code of IEEE TPAMI 2025 "Hyper-YOLO: When Visual Object Detection Meets Hypergraph Computation".
  ☆117Updated last year
• lidc1004 / Object-detection-converts
  Objects365/COCO数据集转换为xml格式，并转为yolo的txt格式，xml数据统计更改
  ☆55Updated 4 years ago
• BooHwang / segment_anything_tensorrt
  Accelerate segment anything model inference using Tensorrt 8.6.1.6
  ☆105Updated 2 years ago
• Xuan-World / Mamba-YOLO-World
  Mamba-YOLO-World: Marrying YOLO-World with Mamba for Open-Vocabulary Detection
  ☆95Updated 10 months ago
• CVHub520 / X-AnyLabeling-Server
  A Simple, Lightweight, and Extensible Serving Framework for X-AnyLabeling
  ☆135Updated last week
• hpc203 / scrfd-opencv
  使用OpenCV部署SCRFD人脸检测，包含C++和Python两种版本的程序实现，本套程序只依赖opencv库就可以运行， 从而彻底摆脱对任何深度学习框架的依赖。
  ☆127Updated 4 years ago
• wanghao9610 / OV-DINO
  OV-DINO: Unified Open-Vocabulary Detection with Language-Aware Selective Fusion
  ☆398Updated 10 months ago
• wingdzero / GroundingDINO-TensorRT-and-ONNX-Inference
  使用TensorRT推理GroundingDINO，推理速度提升3倍以上！
  ☆53Updated last year
• gyhdc / LabelSAM-for-yolo
  简易的yolo半自动标注库，目前只支持单目标。如果数据集图片背景复杂，可能工作量不比直接标的小，因为sam是通用的分割模型。但是可以适当通过调整参数修改。
  ☆135Updated 2 years ago
• haochenheheda / segment-anything-annotator
  We developed a python UI based on labelme and segment-anything for pixel-level annotation. It support multiple masks generation by SAM(bo…
  ☆384Updated 2 years ago
• shuyansy / Detect-and-read-meters
  This is the first released system towards complex meters` detection and recognition, which is implemented by computer vision techniques.
  ☆184Updated 2 years ago
• Tencent / YOLO-Master
  🚀🚀🚀Official code for the paper "YOLO-Master: MOE-Accelerated with Specialized Transformers for Enhanced Real-time Detection." *(YO…
  ☆340Updated last week
• miquel-espinosa / no-time-to-train
  Official code for "No time to train! Training-Free Reference-Based Instance Segmentation"
  ☆278Updated this week
• lorebianchi98 / CountingDINO
  [WACV 2026] Official implementation of the paper: “CountingDINO: A Training-free Pipeline for Exemplar-based Class-Agnostic Counting”
  ☆44Updated 3 months ago
• ChuRuaNh0 / FastSam_Awsome_TensorRT
  ☆130Updated 2 years ago
• PaddlePaddle / PaddleSports
  ☆122Updated 2 years ago
• little51 / dinov3-train
  DINOv3训练示例
  ☆138Updated 2 months ago
• mingj2021 / segment-anything-tensorrt
  ☆79Updated 2 years ago
• zap200281 / PLabel
  半自动标注系统是基于BS架构，由鹏城实验室自主研发，集成视频抽帧，目标检测、视频跟踪、ReID分类、人脸检测等算法，实现了对图像，视频的自动标注，并可以对自动算法的结果进行人工标注，最终得到标注结果，同时也可以对视频、图片、医疗（包括dicom文件及病理图像）相关的数据进行…
  ☆194Updated 2 years ago