[TOG 2021] SofGAN: A Portrait Image Generator with Dynamic Styling

SwinIR: Image Restoration Using Swin Transformer

PyTorch codes for "Progressive Semantic-Aware Style Transformation for Blind Face Restoration", CVPR2021

Flickr-Faces-HQ Dataset (FFHQ)

Rethinking Image Inpainting via a Mutual Encoder Decoder with Feature Equalizations. ECCV 2020 Oral

EdgeConnect: Structure Guided Image Inpainting using Edge Prediction, ICCV 2019 https://arxiv.org/abs/1901.00212

StyleGAN Encoder - converts real images to latent space

Benchmark datasets and code used in our paper "DoveNet: Deep Image Harmonization via Domain Verification", CVPR2020. Useful for Image harmonization, image composition/compositing, etc.

Face Analysis Project on MXNet

chinese characters recognition

Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more

Configure Caffe in one hour for Windows users.

Gluon CV Toolkit

Caffe: a fast open framework for deep learning.

Feature Pyramid Networks for Object Detection

Caffe implementation of SSD and SSDLite detection on MobileNetv2, converted from tensorflow.

Person Re-ranking (CVPR 2017)

Caffe implementation of Google MobileNet SSD detection network, with pretrained weights on VOC0712 and mAP=0.727.

Fully Convolutional Networks for Semantic Segmentation by Jonathan Long*, Evan Shelhamer*, and Trevor Darrell. CVPR 2015 and PAMI 2016.

Gluon Implementation of Single Shot MultiBox Detector(SSD)

Caffe Implementation of Google's MobileNets (v1 and v2)

Unsupervised Learning using Videos (ICCV 2015)

Domain Guided Dropout for Person Re-identification

A Discriminatively Learned CNN Embedding for Person Re-identification

🌁 Image retrieval using deep learning of global descriptors.

Fashion Landmark Detection in the Wild

Person Re-Identification: Multi-Task Deep CNN with Triplet Loss