MapAnything: Universal Feed-Forward Metric 3D Reconstruction

Photoshop CC v19 installer for Gnu/Linux

Fast Optical Flow using Dense Inverse Search (DIS)

One-paper-one-short-contribution-summary of all latest image/burst/video Denoising papers with code & citation published in top conference and journal.

vim配置文件和插件(不再维护)

A lite C++ AI toolkit: 100+ models with MNN, ORT and TRT, including Det, Seg, Stable-Diffusion, Face-Fusion.

golang写的电子商城的API接口

LabelImg is now part of the Label Studio community. The popular image annotation tool created by Tzutalin is no longer actively being developed, but you can check out Label Studio, the open source …

传统的图像处理相关算法的代码实现

Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

ICCV2021, Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet

Crack LeetCode, not only how, but also why.

A Unified Toolkit for Deep Learning Based Document Image Analysis

Deep learning based page layout analysis

OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation

Real-Time and Accurate Full-Body Multi-Person Pose Estimation&Tracking System

This demo shows you how to build a single pose estimation algorithm in C++ using libtorch The model is trained using pytorch (Alphapose's SPPE model) , Check their github for training the model

Halpe: full body human pose estimation and human-object interaction detection dataset

人像matting数据集，包含34427张图像和对应的matting结果图。

ocr with yolo3 as feature extractor, implemented by keras, and accelerated by tensorrt

The pytorch re-implement of the official efficientdet with SOTA performance in real time and pretrained weights.

PyTorch implementation of the U-Net for image semantic segmentation with high quality images

H5 video filter

CTPN + DenseNet + CTC based end-to-end Chinese OCR implemented using tensorflow and keras

公式图片ocr，输入图片输出对应的latex表达式

PyTorch implementation of YOLOv3, YOLOv3-SPP, and YOLOv3-tiny for real-time object detection with training, validation, inference, and multi-format export.

Document Rectification and Illumination Correction using a Patch-based CNN