CV Code | 本周新出计算机视觉开源代码汇总（含自动驾驶目标检测、医学图像分割、风格迁移、语义分割、目标跟踪等）

刚刚过去的一周含五一假期，工作日第一天，CV君汇总了过去一周计算机视觉领域新出的开源代码，涉及到自动驾驶目标检测、医学图像分割、风格迁移、神经架构搜索、图卷积神经网络、网络减枝、语义分割、目标跟踪等，含多篇CVPR 2019的论文的代码实现。

可能是大部分华人在放假吧，感觉开源工程比之前少一点。

希望对你有帮助～

ICIP 2019

用于自动驾驶汽车目标检测的雷达区域候选网络

RRPN: Radar Region Proposal Network for Object Detection in Autonomous Vehicles

Ramin Nabati, Hairong Qi

http://arxiv.org/abs/1905.00526v1

https://github.com/mrnabati/RRPN

用于自动驾驶汽车感知的精确的合成图像与LiDAR数据集

Precise Synthetic Image and LiDAR (PreSIL) Dataset for Autonomous Vehicle Perception

Braden Hurl, Krzysztof Czarnecki, Steven Waslander

https://arxiv.org/abs/1905.00160v1

https://uwaterloo.ca/waterloo-intelligent-systems-engineering-lab/projects/precise-synthetic-image-and-lidar-presil-dataset-autonomous

CT医学图像重建高级框架PYRO-NN，构建于TensorFlow之上

PYRO-NN: Python Reconstruction Operators in Neural Networks

Christopher Syben, Markus Michen, Bernhard Stimpel, Stephan Seitz, Stefan Ploner, Andreas K. Maier

https://arxiv.org/abs/1904.13342v1

https://github.com/csyben/PYRO-NN

跨图像库检测未知但相同目标类

Learning to Find Common Objects Across Image Collections

Amirreza Shaban, Amir Rahimi, Stephen Gould, Byron Boots, Richard Hartley

https://arxiv.org/abs/1904.12936v1

https://github.com/haamoon/finding_common_object

CVPR 2019

风格迁移

Style Transfer by Relaxed Optimal Transport and Self-Similarity

Nicholas Kolkin, Jason Salavon, Greg Shakhnarovich

https://arxiv.org/abs/1904.12785v1

https://github.com/nkolkin13/STROTSS

神经架构搜索

Progressive Differentiable Architecture Search: Bridging the Depth Gap between Search and Evaluation

Xin Chen, Lingxi Xie, Jun Wu, Qi Tian

https://arxiv.org/abs/1904.12760v1

https://github.com/chenxin061/pdarts

图卷积神经网络，点云的非监督特征学习

Unsupervised Feature Learning for Point Cloud by Contrasting and Clustering With Graph Convolutional Neural Network

Ling Zhang, Zhigang Zhu

https://arxiv.org/abs/1904.12359v1

https://github.com/lingzhang1/ContrastNet

网络压缩，滤波剪枝

LeGR: Filter Pruning via Learned Global Ranking

Ting-Wu Chin, Ruizhou Ding, Cha Zhang, Diana Marculescu

https://arxiv.org/abs/1904.12368v1

https://github.com/cmu-enyac/LeGR

高分辨率网络用于逼真风格迁移

这里的高分辨率网络就是CV君曾经介绍过的：

分割、检测与定位，高分辨率网络显神威！这会是席卷深度学习的通用结构吗？

技术进步真的好快啊！

High-Resolution Network for Photorealistic Style Transfer

Ming Li, Chunyang Ye, Wei Li

https://arxiv.org/abs/1904.11617v1

https://github.com/limingcv/Photorealistic-Style-Transfer

CVPR 2019 Oral

神经架构搜索自动设计语义分割网络Auto-DeepLab

Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation

Chenxi Liu, Liang-Chieh Chen, Florian Schroff, Hartwig Adam, Wei Hua, Alan Yuille, Li Fei-Fei

https://arxiv.org/abs/1901.02985

https://github.com/tensorflow/models/tree/master/research/deeplab （官方）

https://github.com/MenghaoGuo/AutoDeeplab （非官方）

CVPR 2019 Oral

目前最强的目标跟踪算法SiamRPN++开源实现

SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks

Bo Li, Wei Wu, Qiang Wang, Fangyi Zhang, Junliang Xing, Junjie Yan

https://arxiv.org/abs/1812.11703

https://github.com/PengBoXiangShang/SiamRPN_plus_plus_PyTorch （非官方）