分割文本_CVPR2019| 0402更新14篇论文及代码（3篇oral、含点云分割、文本检测、视频合成等）...

加入极市专业CV交流群，与6000+来自腾讯，华为，百度，北大，清华，中科院等名企名校视觉开发者互动交流！更有机会与李开复老师等大牛群内互动！

同时提供每月大咖直播分享、真实项目需求对接、干货资讯汇总，行业技术交流。点击文末“”立刻申请入群~

前段时间，计算机视觉顶会CVPR 2019 公布了接收结果，极市也对此做了相关报道：1300篇！CVPR2019接收结果公布，你中了吗？。目前官方只公布了接收论文ID列表，极市已汇总目前公开的所有论文链接及code(目前已更新319篇)，今日更新论文如下：

CVPR2019 全部论文汇总：

https://github.com/extreme-assistant/cvpr2019

CVPR2019 论文解读

http://bbs.cvmart.net/topics/287/cvpr2019

1.DVC: An End-to-end Deep Video Compression Framework(Oral) 
作者：Guo Lu, Wanli Ouyang, Dong Xu, Xiaoyun Zhang, Chunlei Cai, Zhiyong Gao 
论文链接：https://arxiv.org/abs/1812.00101代码链接：https://github.com/GuoLusjtu/DVC 

2.Multispectral Imaging for Fine-Grained Recognition of Powders on Complex Backgrounds(Oral) 
作者：Tiancheng Zhi, Bernardo R. Pires, Martial Hebert and Srinivasa G. Narasimhan 
论文链接：

http://www.cs.cmu.edu/~ILIM/projects/IM/MSPowder/files/ZPHN-CVPR19.pdf代码链接：

https://github.com/tiancheng-zhi/ms-powder项目链接：

http://www.cs.cmu.edu/~ILIM/projects/IM/MSPowder/ 

3.Single Image Reflection Removal Exploiting Misaligned Training Data and Network Enhancements 
作者：Kaixuan Wei, Jiaolong Yang, Ying Fu, David Wipf, Hua Huang 
论文链接：https://arxiv.org/abs/1904.00637代码链接：

https://github.com/Vandermode/ERRNet 

4.Convolutional Neural Networks Deceived by Visual Illusions 
作者：Alexander Gomez-Villa, Adrián Martín, Javier Vazquez-Corral, Marcelo Bertalmío 
论文链接：https://arxiv.org/abs/1811.10565 

5.NM-Net: Mining Reliable Neighbors for Robust Feature Correspondences 
作者：Chen Zhao, Zhiguo Cao, Chi Li, Xin Li, Jiaqi Yang 
论文链接：https://arxiv.org/abs/1904.00320 

6.Fully Learnable Group Convolution for Acceleration of Deep Neural Networks 
作者：Xijun Wang, Meina Kan, Shiguang Shan, Xilin Chen 
论文链接：https://arxiv.org/abs/1904.00346 

7.Perceive Where to Focus: Learning Visibility-aware Part-level Features for Partial Person Re-identification 
作者：Yifan Sun, Qin Xu, Yali Li, Chi Zhang, Yikang Li, Shengjin Wang, Jian Sun 
论文链接：https://arxiv.org/abs/1904.00537 

8.Scene Graph Generation with External Knowledge and Image Reconstruction 
作者：Jiuxiang Gu, Handong Zhao, Zhe Lin, Sheng Li, Jianfei Cai, Mingyang Ling 
论文链接：https://arxiv.org/abs/1904.00560 
9.Multi-source weak supervision for saliency detection 
作者：Yu Zeng, Yunzhi Zhuge, Huchuan Lu, Lihe Zhang, Mingyang Qian, Yizhou Yu 
论文链接：https://arxiv.org/abs/1904.00566 

10.Single Image Reflection Removal Exploiting Misaligned Training Data and Network Enhancements 
作者：Kaixuan Wei, Jiaolong Yang, Ying Fu, David Wipf, Hua Huang 
论文链接：https://arxiv.org/abs/1904.00637代码链接：

https://github.com/Vandermode/ERRNet 

11.End-to-End Time-Lapse Video Synthesis from a Single Outdoor Image 
作者：Seonghyeon Nam, Chongyang Ma, Menglei Chai, William Brendel, Ning Xu, Seon Joo Kim 
论文链接：https://arxiv.org/abs/1904.00680 

12.JSIS3D: Joint Semantic-Instance Segmentation of 3D Point Clouds with Multi-Task Pointwise Networks and Multi-Value Conditional Random Fields(Oral)

作者：Quang-Hieu Pham, Duc Thanh Nguyen, Binh-Son Hua, Gemma Roig, Sai-Kit Yeung 
论文链接：https://arxiv.org/abs/1904.00699项目链接：https://pqhieu.github.io/cvpr19.html 

13.Tightness-aware Evaluation Protocol for Scene Text Detection 
作者：Yuliang Liu, Lianwen Jin, Zecheng Xie, Canjie Luo, Shuaitao Zhang, Lele Xie 
论文链接：https://arxiv.org/abs/1904.00813 

14.Precise Detection in Densely Packed Scenes 
作者：Eran Goldman , Roei Herzig, Aviv Eisenschtat, Jacob Goldberger, Tal Hassner 
论文链接：https://arxiv.org/abs/1904.00853 

*延伸阅读

关于本次CVPR2019投稿的一些感想

CVPR2019 论文解读汇总(更新中)

点击左下角“”，即可申请加入极市目标跟踪、目标检测、工业检测、人脸方向、视觉竞赛等技术交流群，更有每月大咖直播分享、真实项目需求对接、干货资讯汇总，行业技术交流，一起来让思想之光照的更远吧~

△长按关注极市平台

觉得有用麻烦给个好看啦~