CV Code | 本周计算机视觉新出开源代码汇总（含目标检测、深度估计、视频识别、网络加速算法等）

计算机视觉技术发展迅速，很多时候，可悲的不是我们没有努力，而是没有跟上时代的步伐。努力coding终于出来结果了，却发现早就有人开源了，效果还比自己写的好！

CV君汇总了一周新出的开源代码，有些很实用，有些很前沿，涉及的方向很多，相信总有一份你需要！

航拍图像中建筑物检测、分割、分类

https://github.com/daveluo/zanzibar-aerial-mapping

图像超分辨率

Image Super-Resolution by Neural Texture Transfer

Zhifei Zhang, Zhaowen Wang, Zhe Lin, Hairong Qi

https://arxiv.org/abs/1903.00834

https://github.com/ZZUTK/SRNTT

视频识别

SlowFast Networks for Video Recognition

Christoph Feichtenhofer, Haoqi Fan, Jitendra Malik, Kaiming He

https://arxiv.org/abs/1812.03982

https://github.com/RI-CH/SlowFastNetworks

深度估计

FastDepth: Fast Monocular Depth Estimation on Embedded Systems

Diana Wofk, Fangchang Ma, Tien-Ju Yang, Sertac Karaman, Vivienne Sze

https://arxiv.org/abs/1903.03273

https://github.com/dwofk/fast-depth

变分自动编码器

Diagnosing and Enhancing VAE Models

Bin Dai, David Wipf

https://arxiv.org/abs/1903.05789v1

https://github.com/daib13/TwoStageVAE

目标检测框架

SimpleDet: A Simple and Versatile Distributed Framework for Object Detection and Instance Recognition

Yuntao Chen, Chenxia Han, Yanghao Li, Zehao Huang, Yi Jiang, Naiyan Wang, Zhaoxiang Zhang

https://arxiv.org/abs/1903.05831v1

https://github.com/tusimple/simpledet

点云配准

PointNetLK: Robust & Efficient Point Cloud Registration using PointNet

Yasuhiro Aoki, Hunter Goforth, Rangaprasad Arun Srivatsan, Simon Lucey

https://arxiv.org/abs/1903.05711v1

https://github.com/hmgoforth/PointNetLK

网络加速与训练技巧

Universally Slimmable Networks and Improved Training Techniques

Jiahui Yu, Thomas Huang

https://arxiv.org/abs/1903.05134v1

https://github.com/JiahuiYu/slimmable_networks

人机交互、触感控制

Manipulation by Feel: Touch-Based Control with Deep Predictive Models

Stephen Tian, Frederik Ebert, Dinesh Jayaraman, Mayur Mudigonda, Chelsea Finn, Roberto Calandra, Sergey Levine

https://arxiv.org/abs/1903.04128v1

https://sites.google.com/view/deeptactilempc

自动生成训练数据

GOGGLES: Automatic Training Data Generation with Affinity Coding

Nilaksh Das, Sanya Chaba, Sakshi Gandhi, Duen Horng Chau, Xu Chu

https://arxiv.org/abs/1903.04552v1

https://github.com/chu-data-lab/GOGGLES/

高效网络设计

Group-wise Correlation Stereo Network

Xiaoyang Guo, Kai Yang, Wukui Yang, Xiaogang Wang, Hongsheng Li

https://arxiv.org/abs/1903.04025v1

https://github.com/xy-guo/GwcNet

拥挤人群图像合成

Learning from Synthetic Data for Crowd Counting in the Wild

Qi Wang, Junyu Gao, Wei Lin, Yuan Yuan

https://arxiv.org/abs/1903.03303v1

https://gjy3035.github.io/GCC-CL/

医学图像配准

Unsupervised Learning of Probabilistic Diffeomorphic Registration for Images and Surfaces

Adrian V. Dalca, Guha Balakrishnan, John Guttag, Mert R. Sabuncu

https://arxiv.org/abs/1903.03545v1

http://voxelmorph.csail.mit.edu/

无监督数据估算，医学图像处理

Unsupervised Data Imputation via Variational Inference of Deep Subspaces

Adrian V. Dalca, John Guttag, Mert R. Sabuncu

https://arxiv.org/abs/1903.03503v1

http://github.com/adalca/neuron

目标检测

ScratchDet:Exploring to Train Single-Shot Object Detectors from Scratch

Rui Zhu, Shifeng Zhang, Xiaobo Wang, Longyin Wen, Hailin Shi, Liefeng Bo, Tao Mei

https://arxiv.org/abs/1810.08425

https://github.com/KimSoybean/ScratchDet

（还未放出，但soon）

支持CV君，请文末点个好看谢谢