hdjsjyl

Multispectral-FCOS

Anchor-less Pedestrian Detection, on KAIST Multispectral Dataset.

antialiased-cnns

Antialiasing cnns to improve stability and accuracy. In ICML 2019.

bottom-up-attention

Bottom-up attention model for image captioning and VQA, based on Faster R-CNN and Visual Genome

C-3-Framework

An open-source PyTorch code for crowd counting

CenterNetPerson

CenterNet used for pedestrian detection

d-SNE

Implementation of our proposed algorithm in domain adaptation for image classification

DeepUPE

Underexposed Photo Enhancement Using Deep Illumination Estimation

densebody_pytorch

PyTorch implementation of CloudWalk's recent work DenseBody

dgcnn

Distilling-Object-Detectors

Implementations of CVPR 2019 paper Distilling Object Detectors with Fine-grained Feature Imitation

EDVR

Winning Solution in NTIRE19 Challenges on Video Restoration and Enhancement (CVPR19 Workshops) - Video Restoration with Enhanced Deformable Convolutional Networks

EfficientNet-PyTorch

A PyTorch implementation of EfficientNet

EnlightenGAN

EnlightenGAN: Deep Light Enhancement without Paired Supervision

ERRNet

Single Image Reflection Removal Exploiting Misaligned Training Data and Network Enhancements (CVPR 2019)

EXTD_Pytorch

Official EXTD Pytorch code

FoveaBox

FoveaBox: Beyond Anchor-based Object Detector

Grid-R-CNN

ImageNet-Adversarial-Training

ImageNet classifier with state-of-the-art adversarial robustness

insightface

Face Analysis Project on MXNet

LLFF

Code release for Local Light Field Fusion at SIGGRAPH 2019

M3D-RPN

mAP

mean Average Precision - This code evaluates the performance of your neural net for object recognition.

Occlusion_Net

Occlusion-Net: 2D/3D Occluded Keypoint Localization Using Graph Networks

pba

Efficient Learning of Augmentation Policy Schedules

PointRCNN

The PyTorch Implementation of PointRCNN for 3D Object Detection from Raw Point Cloud, CVPR 2019.

pvnet

Code for "PVNet: Pixel-wise Voting Network for 6DoF Pose Estimation" CVPR 2019 oral

RepPoints

Represent Visual Objects by Point Sets

RFB-Person

利用RFB进行行人检测的基线代码

second.pytorch

SECOND for KITTI/NuScenes object detection

ZQCNN

一款比mini-caffe更快的Forward库，觉得好用请点星啊，400星公布快速人脸检测模型，500星公布106点landmark，600星公布人头检测模型，700星公布人脸检测套餐（六种pnet,两种rnet随意混合使用满足各种速度/精度要求），800星公布更准的106点模型