点击我爱计算机视觉标星，更快获取CVML新技术

---

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君汇总了最近过去的一周新出的开源代码，包括方向有目标检测、深度估计、行人重识别、实例分割、姿态估计、超分辨率、行人检测、神经架构搜索等，还有一些新出的机器学习范式如长尾识别问题。希望对大家有启发。

ps.以下列出的代码网址中，有少部分代码还未放出。

Instance Segmentation of Biological Images Using Harmonic Embeddings

Victor Kulikov, Victor Lempitsky

https://arxiv.org/abs/1904.05257v1

https://github.com/kulikovv/harmonic

CVPR 2019 Oral

Large-Scale Long-Tailed Recognition in an Open World

Ziwei Liu, Zhongqi Miao, Xiaohang Zhan, Jiayun Wang, Boqing Gong, Stella X. Yu

https://arxiv.org/abs/1904.05160v1

https://liuziwei7.github.io/projects/LongTail.html

Spherical Regression: Learning Viewpoints, Surface Normals and 3D Rotations on n-Spheres

Shuai Liao, Efstratios Gavves, Cees G. M. Snoek

https://arxiv.org/abs/1904.05404v1

https://github.com/leoshine/Spherical_Regression

CVPR 2019

Expressive Body Capture: 3D Hands, Face, and Body from a Single Image

Georgios Pavlakos, Vasileios Choutas, Nima Ghorbani, Timo Bolkart, Ahmed A. A. Osman, Dimitrios Tzionas, Michael J. Black

https://arxiv.org/abs/1904.05866v1

https://smpl-x.is.tue.mpg.de/

Two Body Problem: Collaborative Visual Task Completion

Unnat Jain, Luca Weihs, Eric Kolve, Mohammad Rastegari, Svetlana Lazebnik, Ali Farhadi, Alexander Schwing, Aniruddha Kembhavi

https://arxiv.org/abs/1904.05879v1

https://prior.allenai.org/projects/two-body-problem

Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network

Chen Li, Gim Hee Lee

https://arxiv.org/abs/1904.05547v1

https://github.com/chaneyddtt/Generating-Multiple-Hypotheses-for-3D-Human-Pose-Estimation-with-Mixture-Density-Network

Generalizing Monocular 3D Human Pose Estimation in the Wild

Luyang Wang, Yan Chen, Zhenhua Guo, Keyuan Qian, Mude Lin, Hongsheng Li, Jimmy S. Ren

https://arxiv.org/abs/1904.05512

https://github.com/llcshappy/Monocular-3D-Human-Pose

CVPR 2019

Reliable and Efficient Image Cropping: A Grid Anchor based Approach

Hui Zeng, Lida Li, Zisheng Cao, Lei Zhang

https://arxiv.org/abs/1904.04441v1

https://github.com/HuiZeng/Grid-Anchor-based-Image-Cropping

High-Resolution Representations for Labeling Pixels and Regions

Ke Sun, Yang Zhao, Borui Jiang, Tianheng Cheng, Bin Xiao, Dong Liu, Yadong Mu, Xinggang Wang, Wenyu Liu, Jingdong Wang

https://arxiv.org/abs/1904.04514v1

https://github.com/HRNet

Adversarial Learning of Disentangled and Generalizable Representations for Visual Attributes

James Oldfield, Yannis Panagakis, Mihalis A. Nicolaou

https://arxiv.org/abs/1904.04772v1

https://github.com/james-oldfield/adv-attribute-disentanglement

Adaptive Morphological Reconstruction for Seeded Image Segmentation

Tao Lei, Xiaohong Jia, Tongliang Liu, Shigang Liu, Hongying Meng, Asoke K. Nandi

https://arxiv.org/abs/1904.03973v1

https://github.com/SUST-reynole/AMR

CVPR 2019

Learning monocular depth estimation infusing traditional stereo knowledge

Fabio Tosi, Filippo Aleotti, Matteo Poggi, Stefano Mattoccia

https://arxiv.org/abs/1904.04144v1

https://github.com/fabiotosi92/monoResMatch-Tensorflow

CVPR 2019

Adaptively Connected Neural Networks

Guangrun Wang, Keze Wang, Liang Lin

https://arxiv.org/abs/1904.03579

https://github.com/wanggrun/Adaptively-Connected-Neural-Networks

Weakly Supervised Person Re-identification: Cost-effective Learning with A New Benchmark

Guangrun Wang, Guangcong Wang, Xujie Zhang, Jianhuang Lai, Liang Lin

https://arxiv.org/abs/1904.03845v1

https://github.com/wanggrun/SYSU-30k

CVPR 2019

Self-supervised Spatio-temporal Representation Learning for Videos by Predicting Motion and Appearance Statistics

Jiangliu Wang, Jianbo Jiao, Linchao Bao, Shengfeng He, Yunhui Liu, Wei Liu

https://arxiv.org/abs/1904.03597v1

https://github.com/laura-wang/video_repres_mas

Stokes Inversion based on Convolutional Neural Networks

A. Asensio Ramos , C. Diaz Baso

https://arxiv.org/abs/1904.03714v1

http://github.com/aasensio/sicon

CVPR 2019

Camera Lens Super-Resolution

Chang Chen, Zhiwei Xiong, Xinmei Tian, Zheng-Jun Zha, Feng Wu

https://arxiv.org/abs/1904.03378v1

https://github.com/ngchc/CameraSR

When AWGN-based Denoiser Meets Real Noises

Yuqian Zhou, Jianbo Jiao, Haibin Huang, Yang Wang, Jue Wang, Honghui Shi, Thomas Huang

https://arxiv.org/abs/1904.03485v1

https://github.com/yzhouas/PD-Denoising-pytorch

Doodle to Search: Practical Zero-Shot Sketch-based Image Retrieval

Sounak Dey, Pau Riba, Anjan Dutta, Josep Llados, Yi-Zhe Song

https://arxiv.org/abs/1904.03451v1

https://sounakdey.github.io/doodle2search.github.io/

Instance-Level Meta Normalization

Songhao Jia, Ding-Jie Chen, Hwann-Tzong Chen

https://arxiv.org/abs/1904.03516v1

https://github.com/Gasoonjia/ILM-Norm

The EntOptLayout Cytoscape plug-in for the efficient visualization of major protein complexes in protein-protein interaction and signalling networks

Bence Agg, Andrea Csaszar, Mate Szalay-Beko, Daniel V. Veres, Reka Mizsei, Peter Ferdinandy, Peter Csermely, Istvan A. Kovacs

https://arxiv.org/abs/1904.03910v1

http://apps.cytoscape.org/apps/entoptlayout

Can GCNs Go as Deep as CNNs?

Guohao Li, Matthias Müller, Ali Thabet, Bernard Ghanem

https://arxiv.org/abs/1904.03751v1

https://sites.google.com/view/deep-gcns

LP-3DCNN: Unveiling Local Phase in 3D Convolutional Neural Networks

Sudhakar Kumawat, Shanmuganathan Raman

https://arxiv.org/abs/1904.03498v1

https://sites.google.com/view/lp-3dcnn/home

Branched Multi-Task Networks: Deciding What Layers To Share

Simon Vandenhende, Bert De Brabandere, Luc Van Gool

https://arxiv.org/abs/1904.02920v1

https://github.com/SimonVandenhende/

3D LiDAR and Stereo Fusion using Stereo Matching Network with Conditional Cost Volume Normalization

Tsun-Hsuan Wang, Hou-Ning Hu, Chieh Hubert Lin, Yi-Hsuan Tsai, Wei-Chen Chiu, Min Sun

https://arxiv.org/abs/1904.02917v1

https://zswang666.github.io/Stereo-LiDAR-CCVNorm-Project-Page/

https://github.com/zswang666/Stereo-LiDAR-CCVNorm

CVPR 2019

High-level Semantic Feature Detection:A New Perspective for Pedestrian Detection

Wei Liu, Shengcai Liao, Weiqiang Ren, Weidong Hu, Yinan Yu

https://arxiv.org/abs/1904.02948v1

https://github.com/liuwei16/CSP

Single-Path NAS: Designing Hardware-Efficient ConvNets in less than 4 Hours

Dimitrios Stamoulis, Ruizhou Ding, Di Wang, Dimitrios Lymberopoulos, Bodhi Priyantha, Jie Liu, Diana Marculescu

https://arxiv.org/abs/1904.02877v1

https://github.com/dstamoulis/single-path-nas

Point-to-Point Video Generation

Tsun-Hsuan Wang, Yen-Chi Cheng, Chieh Hubert Lin, Hwann-Tzong Chen, Min Sun

https://arxiv.org/abs/1904.02912v1

https://zswang666.github.io/P2PVG-Project-Page/

支持CV君，请文末点个“在看”，谢谢～

加群交流

关注计算机视觉与机器学习技术，欢迎加入52CV群，扫码添加52CV君拉你入群，

（请务必注明:52CV）

喜欢在QQ交流的童鞋，可以加52CV官方QQ群：702781905。

（不会时时在线，如果没能及时通过验证还请见谅）

---

长按关注我爱计算机视觉