alexsibir

gangealing

Official PyTorch Implementation of "GAN-Supervised Dense Visual Alignment" (CVPR 2022 Oral, Best Paper Finalist)

GPNN

Pytorch implementation of the paper: "Drop the GAN: In Defense of Patches Nearest Neighbors as Single Image Generative Models"

piq

Measures and metrics for image2image tasks. PyTorch.

image-size-scanner

Scans image files and extracts image sizes, no image decoding, no dependencies.

SegLossOdyssey

A collection of loss functions for medical image segmentation

roc-star

Loss function which directly targets ROC-AUC

first-order-model

This repository contains the source code for the paper First Order Motion Model for Image Animation

first-order-model

This repository contains the source code for the paper First Order Motion Model for Image Animation

heatmap-based-landmarker

An Implementation of Heatmap Regression via Randomized Rounding

Face-SPARNet

Pytorch codes for "Learning Spatial Attention for Face Super-Resolution", TIP 2020.

distributed-pytorch

Distributed, mixed-precision training with PyTorch

distributed_tutorial

Face-Detector-1MB-with-landmark

1M人脸检测模型(含关键点)

Ultra-Light-Fast-Generic-Face-Detector-1MB

💎1MB lightweight face detection model (1MB轻量级人脸检测模型)

parallelpipe

Pipeline parallelization library

WB_color_augmenter

WB color augmenter improves the accuracy of image classification and image semantic segmentation methods by emulating different WB effects (ICCV 2019) [Python & Matlab].

fast-reid

SOTA Re-identification Methods and Toolbox

ttach

Image Test Time Augmentation with PyTorch!

paper-code-classified-summary

【我爱计算机视觉】微信公众号整理：2021年CV 最新综述/WACV 2021/ECCV 2020/CVPR 2020 paper-code【更新中】

nanodet

NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥

mobile-hair-segmentation-pytorch

Re-implementation Real-time deep hair matting on mobile devices on pytorch

Efficient-Computing

Efficient computing methods developed by Huawei Noah's Ark Lab

Pixel-Art

We implement the famous "Depixelizing Pixel Art" paper by Kopf and Lischinski

depixel

Depixeling tool, based on "Depixelizing Pixel Art".

Noisesniffer

Source code of the article ''Noisesniffer: a Fully Automatic Image Forgery Detector Based on Noise Analysis" published in IWBF 2021.

pytorch-video-pipeline

Image-Forgery-Detection

yoto_class_balanced_loss

Unofficial implementation of YOTO (You Only Train Once) applied to Class balanced loss

Holocron

PyTorch implementations of recent Computer Vision tricks (ReXNet, RepVGG, Unet3p, YOLOv4, CIoU loss, AdaBelief, PolyLoss, MobileOne)

NRVQA

no reference image/video quaity assessment(BRISQUE/NIQE/PIQE/DIQA/deepBIQ/VSFA