【今日CS 视觉论文速览】Fri, 18 Jan 2019

今日CS.CV计算机视觉论文速览
Fri, 18 Jan 2019
Totally 31 papers
添加>>>>:第二部分

Interesting:

用于水下图片增强的基准数据集UIRBD,包含了950张真实水下图片和890张对应的参考图片。同时作者还提出了水下图像提升网络（Deep Underwater ImageEnhancement Network ，DUIENet)，来评估数据集的有效性。(from 香港城市大学)

文中提出的网络结构如下图所示：

（其中字母含义->White Balance (WB), Histogram Equalization (HE) and Gamma Correction (GC)）
website:https://li-chongyi.github.io/homepage.github.io/proj_benchmark.html
相关数据集：
Fish4Knowledge http://groups.inf.ed.ac.uk/f4k/
SUN http://groups.csail.mit.edu/vision/SUN/
MARIS dataset http://rimlab.ce.unipr.it/Maris.html
生成参考数据的相关方法：Fusion-based, Retinex-based, UDCP， Red Channel, Histogram Prior, Blurriness-based, GDCP, dive+.
BGSNet-D,基于卷积网络减去深度图的背景,可用于缺乏光照或者颜色分割不可用的区域。文章中还提出了噪声抑制的方法。（from 中科院）

流程图：

一些结果：

数据集：SBM-RGBD, related Methods, paper
数据集库
Soft Rasterizer,一种用于单视角非监督体网格(Mesh)重建的可微分渲染方法。（from 南加州大学创意技术研究所 &Pinscreen）

三角片的概率图：

基于单视角图片渲染出三维mesh的流程图：

得到的一些结果：

shapeNet dataset

Daily Computer Vision Papers

[1] Title: Semantic Nighttime Image Segmentation with Synthetic Stylized Data， Gradual Adaptation and Uncertainty-Aware Evaluation
Authors:Christos Sakaridis, Dengxin Dai, Luc Van Gool
[2] Title: Foreground-aware Image Inpainting
Authors:Wei Xiong, Zhe Lin, Jimei Yang, Xin Lu, Connelly Barnes, Jiebo Luo
[3] Title: A Performance Comparison of Loss Functions for Deep Face Recognition
Authors:Yash Srivastava, Vaishnav Murali, Shiv Ram Dubey
[4] Title: LiSHT: Non-Parametric Linearly Scaled Hyperbolic Tangent Activation Function for Neural Networks
Authors:Swalpa Kumar Roy, Suvojit Manna, Shiv Ram Dubey, Bidyut B. Chaudhuri
[5] Title: EAT-NAS: Elastic Architecture Transfer for Accelerating Large-scale Neural Architecture Search
Authors:Jiemin Fang, Yukang Chen, Xinbang Zhang, Qian Zhang, Chang Huang, Gaofeng Meng, Wenyu Liu, Xinggang Wang
[6] Title: UltraCompression: Framework for High Density Compression of Ultrasound Volumes using Physics Modeling Deep Neural Networks
Authors:Debarghya China, Francis Tom, Sumanth Nandamuri, Aupendu Kar, Mukundhan Srinivasan, Pabitra Mitra, Debdoot Sheet
[7] Title: Residual Attention based Network for Hand Bone Age Assessment
Authors:Eric Wu, Bin Kong, Xin Wang, Junjie Bai, Yi Lu, Feng Gao, Shaoting Zhang, Kunlin Cao, Qi Song, Siwei Lyu, Youbing Yin
[8] Title: No reference image quality assessment metric based on regional mutual information among images
Authors:Vinay Kumar, Vivek Singh Bawa
[9] Title: AuxNet: Auxiliary tasks enhanced Semantic Segmentation for Automated Driving
Authors:Sumanth Chennupati, Ganesh Sistu, Senthil Yogamani, Samir Rawashdeh
[10] Title: Towards Building the Semantic Map from a Monocular Camera with a Multi-task Network
Authors:Lei Fan, Yucai Bai, Ziyu Pan, Long Chen
[11] Title: Ensemble Feature for Person Re-Identification
Authors:Jiabao Wang, Yang Li, Zhuang Miao
[12] Title: Cone-beam CT to Planning CT synthesis using generative adversarial networks
Authors:S. Kida, S. Kaji, K. Nawa, T. Imae, T. Nakamoto, S. Ozaki, T. Ohta, Y. Nozawa, K. Nakagawa
[13] Title: SAFE: Scale Aware Feature Encoder for Scene Text Recognition
Authors:Wei Liu, Chaofeng Chen, Kwan-Yee K. Wong
[14] Title: Video-Based Pedestrian Attribute Recognition
Authors:Zhiyuan Chen, Annan Li, Yunhong Wang
[15] Title: Multiple Sclerosis Lesion Synthesis in MRI using an encoder-decoder U-NET
Authors:Mostafa Salem, Sergi Valverde, Mariano Cabezas, Deborah Pareto, Arnau Oliver, Joaquim Salvi, Àlex Rovira, Xavier Lladó
[16] Title: Image Enhancement Network Trained by Using HDR images
Authors:Yuma Kinoshita, Hitoshi Kiya
[17] Title: Background subtraction on depth videos with convolutional neural networks
Authors:Xueying Wang, Lei Liu, Guangli Li, Xiao Dong, Peng Zhao, Xiaobing Feng
[18] Title: Certainty-Driven Consistency Loss for Semi-supervised Learning
Authors:Yingting Li, Lu Liu, Robby T. Tan
[19] Title: Enhance the Motion Cues for Face Anti-Spoofing using CNN-LSTM Architecture
Authors:Xiaoguang Tu, Hengsheng Zhang, Mei Xie, Yao Luo, Yuefei Zhang, Zheng Ma
[20] Title: Cognitive Analysis of 360 degree Surround Photos
Authors:Madhawa Vidanapathirana, Lakmal Meegahapola, Indika Perera
[21] Title: Deep Transfer Across Domains for Face Anti-spoofing
Authors:Xiaoguang Tu, Hengsheng Zhang, Mei Xie, Yao Luo, Yuefei Zhang, Zheng Ma
[22] Title: Hand Sign to Bangla Speech: A Deep Learning in Vision based system for Recognizing Hand Sign Digits and Generating Bangla Speech
Authors:Shahjalal Ahmed, Md. Rafiqul Islam, Jahid Hassan, Minhaz Uddin Ahmed, Bilkis Jamal Ferdosi, Sanjay Saha, Md. Shopon
[23] Title: Learning Generalizable and Identity-Discriminative Representations for Face Anti-Spoofing
Authors:Xiaoguang Tu, Jian Zhao, Mei Xie, Guodong Du, Hengsheng Zhang, Jianshu Li, Zheng Ma, Jiashi Feng
[24] Title: Soft Rasterizer: Differentiable Rendering for Unsupervised Single-View Mesh Reconstruction
Authors:Shichen Liu, Weikai Chen, Tianye Li, Hao Li
[25] Title: Visual Feature Fusion and its Application to Support Unsupervised Clustering Tasks
Authors:Gladys Hilasaca, Fernando Paulovich
[26] Title: Class-Balanced Loss Based on Effective Number of Samples
Authors:Yin Cui, Menglin Jia, Tsung-Yi Lin, Yang Song, Serge Belongie
[27] Title: Primitive-based 3D Building Modeling, Sensor Simulation, and Estimation
Authors:Xia Li, Yen-Liang Lin, James Miller, Alex Cheon, Walt Dixon
[28] Title: Conditional Domain Adaptation GANs for Biomedical Image Segmentation
Authors:Hugo Oliveira, Edemir Ferreira, Jefersson A. dos Santos
[29] Title: Response to “Visual Dialogue without Vision or Dialogue” (Massiceti et al., 2018)
Authors:Abhishek Das, Devi Parikh, Dhruv Batra
[30] Title: An Underwater Image Enhancement Benchmark Dataset and Beyond
Authors:Chongyi Li, Chunle Guo, Wenqi Ren, Runmin Cong, Junhui Hou, Sam Kwong, Dacheng Tao
[31] Title: Unsupervised Graph-based Rank Aggregation for Improved Retrieval
Authors:Icaro Cavalcante Dourado, Daniel Carlos Guimarães Pedronette, Ricardo da Silva Torres

Papers from arxiv.org

更多精彩请移步主页

pic from pixels.com