CV Code | 本周新出计算机视觉开源代码汇总（含图像修复、目标检测、医学图像分割、度量学习等）（转自CV君）2019年4月19日_learning a no-reference quality assessment model o-CSDN博客

CV君汇总了过去一周计算机视觉领域新出的开源代码，涉及到图像质量评价、图像去雾、图像修复、医学图像分割、目标检测、人脸对齐、度量学习等，其中有多篇来自CVPR 2019的论文代码。

希望对你有帮助～

非参图像质量评价
Learning a No-Reference Quality Assessment Model of Enhanced Images With Big Data
Ke Gu, Dacheng Tao, Junfei Qiao, Weisi Lin
https://arxiv.org/abs/1904.08632v1
https://sites.google.com/site/guke198701/publications

多任务学习
CVPR 2019
Attentive Single-Tasking of Multiple Tasks
Kevis-Kokitsi Maninis, Ilija Radosavovic, Iasonas Kokkinos
https://arxiv.org/abs/1904.08918v1
http://vision.ee.ethz.ch/~kmaninis/astmt/

图像去雾
Fast Single Image Dehazing via Multilevel Wavelet Transform based Optimization
Jiaxi He, Frank Z. Xing, Ran Yang, Cishen Zhang
https://arxiv.org/abs/1904.08573v1
http://github.com/JiaxiHe/Image-and-Video-Dehazing

目标检测
CenterNet: Keypoint Triplets for Object Detection
Kaiwen Duan, Song Bai, Lingxi Xie, Honggang Qi, Qingming Huang, Qi Tian
https://arxiv.org/abs/1904.08189v2
https://github.com/Duankaiwen/CenterNet

序列识别
CVPR 2019
Aggregation Cross-Entropy for Sequence Recognition
Zecheng Xie, Yaoxiong Huang, Yuanzhi Zhu, Lianwen Jin, Yuliang Liu, Lele Xie
https://arxiv.org/abs/1904.08364v2
https://github.com/summerlvsong/Aggregation-Cross-Entropy

去噪图像的训练数据生成
Generating Training Data for Denoising Real RGB Images via Camera Pipeline Simulation
Ronnachai Jaroensri, Camille Biscarrat, Miika Aittala, Frédo Durand
https://arxiv.org/abs/1904.08825v1
（将要开源，还未放出地址）

图像修复
Deep Fusion Network for Image Completion
Xin Hong, Pengfei Xiong, Renhe Ji, Haoqiang Fan
https://arxiv.org/abs/1904.08060v1
https://github.com/hughplay/DFNet

医学图像分割
nnU-Net: Breaking the Spell on Successful Medical Image Segmentation
Fabian Isensee, Jens Petersen, Simon A. A. Kohl, Paul F. Jäger, Klaus H. Maier-Hein
https://arxiv.org/abs/1904.08128v1
https://github.com/MIC-DKFZ/nnunet

视觉问答
Question Guided Modular Routing Networks for Visual Question Answering
Yanze Wu, Qiang Sun, Jianqi Ma, Bin Li, Yanwei Fu, Yao Peng, Xiangyang Xue
https://arxiv.org/abs/1904.08324v1
（将要开源，还未放出地址）

数据重采样
CVPR 2019
REPAIR: Removing Representation Bias by Dataset Resampling
Yi Li, Nuno Vasconcelos
https://arxiv.org/abs/1904.07911v1
https://github.com/JerryYLi/Dataset-REPAIR/

人脸对齐
Adaptive Wing Loss for Robust Face Alignment via Heatmap Regression
Xinyao Wang, Liefeng Bo, Li Fuxin
https://arxiv.org/abs/1904.07399v1
（将要开源，还未放出地址）

动作检测
Decoupling Localization and Classification in Single Shot Temporal Action Detection
Yupan Huang, Qi Dai, Yutong Lu
https://arxiv.org/abs/1904.07442v1
https://github.com/HYPJUDY/Decouple-SSAD

手部抓取动作的分析与预测
CVPR 2019 Oral
ContactDB: Analyzing and Predicting Grasp Contact via Thermal Imaging
Samarth Brahmbhatt, Cusuh Ham, Charles C. Kemp, James Hays
https://arxiv.org/abs/1904.06830v1
https://contactdb.cc.gatech.edu/

深度度量学习
CVPR 2019
Multi-Similarity Loss with General Pair Weighting for Deep Metric Learning
Xun Wang, Xintong Han, Weiling Huang, Dengke Dong, Matthew R. Scott
https://arxiv.org/abs/1904.06627v1
https://github.com/MalongTech/research-ms-loss