CVPR2019| 04-24更新12篇论文及代码（位姿估计/自动驾驶/GAN/图像生成等）

2019 年 4 月 24 日 极市平台

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“阅读原文”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510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.Unsupervised Person Image Generation with Semantic Parsing Transformation
作者：Sijie Song, Wei Zhang, Jiaying Liu, Tao Mei
论文链接：https://arxiv.org/abs/1904.03379
项目链接：

https://github.com/SijieSong/person_generation_spt

2.Binary Ensemble Neural Network: More Bits per Network or More Networks per Bit?
作者：Shilin Zhu, Xin Dong, Hao Su
论文链接：https://arxiv.org/abs/1806.07550

3.Self-Supervised GANs via Auxiliary Rotation Loss
作者：Ting Chen, Xiaohua Zhai, Marvin Ritter, Mario Lucic, Neil Houlsby
论文链接：https://arxiv.org/abs/1811.11212

4.Multi-Agent Tensor Fusion for Contextual Trajectory Prediction
作者：Tianyang Zhao, Yifei Xu, Mathew Monfort, Wongun Choi, Chris Baker, Yibiao Zhao, Yizhou Wang, Ying Nian Wu
论文链接：https://arxiv.org/abs/1904.04776

5.L3-Net: Towards Learning based LiDAR Localization for Autonomous Driving
作者：Weixin Lu， Yao Zhou， Guowei Wan，Shenhua Hou，Shiyu Song
论文链接：

https://songshiyu01.github.io/pdf/L3Net_W.Lu_Y.Zhou_S.Song_CVPR2019.pdf

6.Deep Convolutional Networks on 3D Point Clouds
作者：Satwik Acharyya, Zhengwu Zhang, Anirban Bhattacharya, Debdeep Pati
论文链接：https://arxiv.org/pdf/1811.07246.pdf
源码链接：

https://github.com/DylanWusee/pointconv

7.CapSal: Leveraging Captioning to Boost Semantics for Salient Object Detection
作者：Lu Zhang; Huchuan Lu ; Zhe Lin ; Jianming Zhang; You He
论文链接：

https://drive.google.com/open?id=1JcZMHBXEX-7AR1P010OXg_wCCC5HukeZ（需要申请）
源码链接：https://github.com/zhangludl/code-and-dataset-for-CapSal

8.Segmentation-driven 6D Object Pose Estimation
作者：Yinlin Hu, Joachim Hugonot, Pascal Fua, Mathieu Salzmann
论文链接：https://arxiv.org/abs/1812.02541
源码链接：https://github.com/cvlab-epfl/segmentation-driven-pose

9.LBS Autoencoder: Self-supervised Fitting of Articulated Meshes to Point Clouds
作者：Chun-Liang Li, Tomas Simon, Jason Saragih, Barnabás Póczos, Yaser Sheikh
论文链接：https://arxiv.org/abs/1904.10037

10.Learning Actor Relation Graphs for Group Activity Recognition
作者：Jianchao Wu, Limin Wang, Li Wang, Jie Guo, Gangshan Wu
论文链接：https://arxiv.org/abs/1904.10117

11.Student Becoming the Master: Knowledge Amalgamation for Joint Scene Parsing, Depth Estimation, and More
作者：Jingwen Ye, Yixin Ji, Xinchao Wang, Kairi Ou, Dapeng Tao, Mingli Song
论文链接：https://arxiv.org/abs/1904.10167

12.Attention-guided Network for Ghost-free High Dynamic Range Imaging
作者：Qingsen Yan, Dong Gong, Qinfeng Shi, Anton van den Hengel, Chunhua Shen, Ian Reid, Yanning Zhang
论文链接：https://arxiv.org/abs/1904.10293