A super-resolution dataset of paired LR-HR scene text images
Statistics for this project are still being loaded, please check back later.
Automated Deep Learning without ANY human intervention. 1'st Solution for AutoDL challenge@NeurIPS.
A collection of pre-trained StyleGAN 2 models to download
OCR-D wrapper for detectron2 based segmentation models
visualization点云可视化(open3D, mayavi, rviz(ros), PCL等)
Visual Attention based OCR
基于语义分割的矿区无人机影像地物提取实验
Base on YOLOv5 Head Person Helmet Detection on Construction Sites,基于目标检测工地安全帽和禁入危险区域识别系统,🚀😆附 YOLO...
基于PaddlePaddle实现的人流密度识别模型CrowdNet
Improved Text recognition algorithms on different text domains like scene text, handwritten, docu...
Official implementation code of the paper <AnyText: Multilingual Visual Text Generation And Editing>
🔥3D点云目标检测&语义分割(深度学习)-SOTA方法,代码,论文,数据集等
[ECCV 2018] CCPD: a diverse and well-annotated dataset for license plate detection and recognition
A high performance impermentation of Unsupervised Image Segmentation by Backpropagation - Asako ...
基于PaddlePaddle实现的SSD,包括MobileNetSSD,MobileNetV2SSD,VGGSSD,ResNetSSD