【今日CV 计算机视觉论文速览】 26 Mar 2019

今日CS.CV计算机视觉论文速览
Tue, 26 Mar 2019
Totally 78 papers
?昨日速览, ✈更多精彩请移步主页

Interesting:

?SRFBN基于反馈网络的图像超分辨, 基于反馈机制和RNN序列来提升图像超分辨效果(from 四川大学)

code:https://github.com/Paper99/SRFBN_CVPR19

?DeepRED,利用去噪的正则化来处理图像逆问题，包括去噪、修复、超分辨等。可以看做是deep image prior的改进 (from Technion,，谷歌)

ref:https://arxiv.org/pdf/1806.02296.pdf
稀疏表示和变换：
http://www4.comp.polyu.edu.hk/~cslzhang/NCSR.htm
http://www.cs.tut.fi/~foi/GCF-BM3D/
相关数据:

?DenseBody, 单张照片生成人体位姿和外形。(from 云从科技)

相关数据集：Human3.6M, SURREAL and UP-3D

?MeshGAN, 非线性3D人脸形变模型，提出了直接处理三维数据的MeshGan(from 帝国理工)

相关数据集合:3dMD,4DFAB
相关方法：CoMA
相关三维卷积：Spectral graph CNNs. Bruna et al. [12] ，ChebNet. Defferrard et al. [22]，f BEGAN [6]
ref:三维运动捕捉公司：http://www.3dmd.com/

?基于R-CNN的虹膜检测系统, 将虹膜作为两个同心圆进行分割,从眼睛图像中分割出不包括瞳孔的虹膜图像(from 昆山杜克大学)

相关数据集：(i) NICE-II and (ii) MICHE (GS4, IP5 and GT2).

?ShopSign, 一个多样性的街道招牌中文文字识别数据集，包含了25362个商店门牌和196010文字行，来源于多种手机拍摄的数据，以及多种不同材质的招牌。(from 河南大学 )

code and dataset:https://github.com/chongshengzhang/shopsign
相关方法： CTPN, TextBoxes++ and EAST
相关数据集：CTW,RCTW,CVPR2018mtmi

---

Daily Computer Vision Papers

1.Title: DeepCenterline: a Multi-task Fully Convolutional Network for Centerline Extraction Authors:Zhihui Guo, Junjie Bai, Yi Lu, Xin Wang, Kunlin Cao, Qi Song, Milan Sonka, Youbing Yin

2.Title: CODA: Counting Objects via Scale-aware Adversarial Density Adaption Authors:Li Wang, Yongbo Li, Xiangyang Xue

3.Title: Scale-Adaptive Neural Dense Features: Learning via Hierarchical Context Aggregation Authors:Jaime Spencer, Richard Bowden, Simon Hadfield

4.Title: Locomotion and gesture tracking in mice and small animals for neurosceince applications: A survey Authors:Waseem Abbas, David Masip Rodo

5.Title: ShopSign: a Diverse Scene Text Dataset of Chinese Shop Signs in Street Views Authors:Chongsheng Zhang, Guowen Peng, Yue