Asphyxiate-Rye

semseg

常用的语义分割架构结构综述以及代码复现 华为媒体研究院 图文Caption、OCR识别、图视文多模态理解与生成相关方向工作或实习欢迎咨询 15757172165 https://guanfuchen.github.io/media/hw_zhaopin_20220724_tiny.jpg

DataDrivenSpaceFillCurve

Research codes of "Data-Driven Space-Filling Curves". Important: main functions are named as "figGenXXX.m". For example, figGenSFC2DCase.m---2D regular grids; figGenSFC3DCase.m---3D regular grids; figGenSFC2DQuadTree.m---2D multiscale; figGenSFC3DOctree.m---3D multiscale.

NeuralSFC

Official Pytorch implementation of the ECCV 2022 paper Neural Space-filling Curves.

mamba

mamba-minimal

Simple, minimal implementation of the Mamba SSM in one file of PyTorch.

vision_mamba

Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

U-Mamba

U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentation

VMamba

VMamba: Visual State Space Models，code is based on mamba

segmentation_models.pytorch

Semantic segmentation models with pretrained backbones. PyTorch.

segformer-pytorch

这是一个segformer-pytorch的源码，可以用于训练自己的模型。

parallelformers

Parallelformers: An Efficient Model Parallelization Toolkit for Deployment

3DSAM-adapter

Holistic Adaptation of SAM from 2D to 3D for Promptable Medical Image Segmentation

Medical-SAM-Adapter

Adapting Segment Anything Model for Medical Image Segmentation

MedSAM

Segment Anything in Medical Images

Book

CLIP-Driven-Universal-Model

[ICCV 2023] CLIP-Driven Universal Model; Rank first in MSD Competition.

MedNeXt

MedNeXt is a fully ConvNeXt architecture for 3D medical image segmentation (MICCAI 2023).

HeartDeformNets

OS-SIFT

ER-Net

mmdetection

OpenMMLab Detection Toolbox and Benchmark

faster-rcnn-pytorch

这是一个faster-rcnn的pytorch实现的库，可以利用voc数据集格式的数据进行训练。

RegistrationMATLABCoursework

Register and analyse two images of different imaging modalities of MRI and Ultrasound.

DFMIR

official implementation of paper "Unsupervised Multi-Modal Medical Image Registration via Discriminator-Free Image-to-Image Translation"

3D-2D-MRI-TVUS-Image-Registration

Implementation of Mapping and Characterizing Endometrial Implants by Registering 2D Transvaginal Ultrasound to 3D Pelvic Magnetic Resonance Images

UA-MT

code for MICCAI 2019 paper 'Uncertainty-aware Self-ensembling Model for Semi-supervised 3D Left Atrium Segmentation'.

SegWithDistMap

How Distance Transform Maps Boost Segmentation CNNs: An Empirical Study

RibSeg

[MICCAI'21 & TMI'23] RibSeg Dataset and Point Cloud Baselines for Rib Segmentation from CT Scans

MICCAI-OpenSourcePapers

MICCAI 2019-2023 Open Source Papers

EfficientUNetPlusPlus

Decoder architecture based on the UNet++. Combining residual bottlenecks with depthwise convolutions and attention mechanisms, it outperforms the UNet++ in a coronary artery segmentation task, while being significantly more computationally efficient.