PaddleSeg是基于飞桨PaddlePaddle开发的端到端图像分割开发套件，涵盖了高精度和轻量级等不同方向的大量高质量分割模型。通过模块化的设计，提供了配置化驱动和API调用两种应用方式，帮助开发者更便捷地完成从训练到部署的全流程图像分割应用。
An OBS plugin for removing background in portrait images (video), making it easy to replace the background when recording or streaming.
翻译 - An OBS plugin for removing background in portrait images (video), making it easy to replace the background when screen recording.
#计算机科学#[ECCV 2022] XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model
Labeling tool with SAM(segment anything model),supports SAM, SAM2, sam-hq, MobileSAM EdgeSAM etc.交互式半自动图像标注工具
#计算机科学#[ICCV 2023] Tracking Anything with Decoupled Video Segmentation
#计算机科学#Visit PixelLib's official documentation https://pixellib.readthedocs.io/en/latest/
A contrastive learning based semi-supervised segmentation network for medical image segmentation
#计算机科学#[CVPR 2024 Highlight] Putting the Object Back Into Video Object Segmentation
PyTorch implementation of One-Shot Video Object Segmentation (OSVOS)
#计算机科学#[NeurIPS 2021] Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation
#计算机科学#[CVPR 2021] Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion. Semi-supervised VOS as well!
Mask-Free Video Instance Segmentation [CVPR 2023]
[ICCV 2023] MOSE: A New Dataset for Video Object Segmentation in Complex Scenes
See More, Know More: Unsupervised Video Object Segmentation with Co-Attention Siamese Networks (CVPR19)
#计算机科学#[CVPR 2017] Unsupervised deep learning using unlabelled videos on the web
#计算机科学#FgSegNet: Foreground Segmentation Network, Foreground Segmentation Using Convolutional Neural Networks for Multiscale Feature Encoding
Learning Unsupervised Video Object Segmentation through Visual Attention (CVPR19, PAMI20)
Pytorch Implementation of "SMITE: Segment Me In TimE" (ICLR 2025)
#计算机科学#[CVPR 2017] Video motion segmentation and tracking
Code release for "UniVS: Unified and Universal Video Segmentation with Prompts as Queries" (CVPR2024)