【今日CV 计算机视觉论文速览】Mon, 25 Mar 2019

今日CS.CV计算机视觉论文速览
Mon, 25 Mar 2019
Totally 21 papers

Interesting:

?图像超分辨的快速贝叶斯不确定性估计，在测试阶段，利用批均值和方差作为批归一化层的随机参数来实现后验概率的蒙特卡洛采样，并给予这些样本进行超分辨率重建和重建的置信度图，并实现了不确定性估计的快速方法。研究人员利用批归一化来实现蒙特卡洛参数的估计，并在测试时使用不同的参数采样出多张图像，由这些图像的均值得到重建结果，图像间的方差作为不确定度度量, (from IIT Kharagpur)
重建结果如下：


常用的数据集：

卫星数据集
细胞数据集
aupendukar@iitkgp.ac.in pkb@ece.iitkgp.ac.in

?利用3D打印件定量测评RGBD相机的参数, 分别利用了柱体、球和带角度的平面测量了RMSE和单位像素密度指标。(from root-ai)

code:https://github.com/Root-AI/depth-quality

?SkelNetOn 2019, cvpr2019几何外形理解挑战赛，数据集中包含了骨架像素、骨架点以及参数化轴和骨架分支结构(from DeepScale,Bergische Universitat Wuppertal, Occidental College, University of Toulouse,University of Basel, 6Dartmouth College, Universite Grenoble Alpes,Princeton University,Johns Hopkins University)

website:http://ubee.enseeiht.fr/skelneton/

?CityFlow, 城市尺度下的多相机、多目标车辆重识别(from 华盛顿大学)
城市相机分布：

标注实例：

坐标图和鸟瞰图配对：

相关重识别数据集：

AI-city Challenge:https://www.aicitychallenge.org/

?1D自编码器重建高角度分辨率散射图(HARDI), 主要用于脑部组织中水散射的方向分布检测，但相比散射张量图像需要更多的测量数据。研究人员利用低分辨数据恢复出高分辨数据来加速这一测试过程，利用压缩感知理论在q空间中采样并重建。(from 华中科技)

取向分布函数（orientation distribution function,ODF）
ODF计算结果：http://dsi-studio.labsolver.org/
ref:http://cmic.cs.ucl.ac.uk/cdmri10/invited_tournier.pdf

?基于解耦表示的多模态图像变形的匹配,利用解耦的图像表示来实现非配对图像的风格迁移Huang et al. [9] and Lee et al. [13],(from 帝国理工)

运动图像，变形场和雅克比测定矩阵：

数据集：COPDGene,BraTS’17

---

Daily Computer Vision Papers

1.Title: On the Importance of Video Action Recognition for Visual Lipreading Authors:Xinshuo Weng

2.Title: Evaluation of a deep learning system for the joint automated detection of diabetic retinopathy and age-related macular degeneration Authors:Cristina González-Gonzalo, Verónica Sánchez-Gutiérrez, Paula Hernández-Martínez, Inés Contreras, Yara T. Lechanteur, Artin Domanian, Bram van Ginneken, Clara I. Sánchez

3.Title: Aggregated Deep Local Features for Remote Sensing Image Retrieval Authors:Raffaele Imbriaco, Clint Sebastian, Egor Bondarev, Peter H.N. de With

4.Title: Factorised Representation Learning in Cardiac Image Analysis Authors:Agisilaos Chartsias, Thomas Joyce, Giorgos Papanastasiou, Michelle Williams, David Newby, Rohan Dharmakumar, Sotirios A. Tsaftaris

5.Title: Fast Bayesian Uncertainty Estimation of Batch Normalized Single Image Super-Resolution Network Authors:Aupendu Kar, Prabir Kumar Biswas

6.Title: Few-shot Adaptive Faster R-CNN Authors:Tao Wang, Xiaopeng Zhang, Li Yuan, Jiashi Feng

7.Title: Joint 3D Face Reconstruction and Dense Face Alignment from A Single Image with 2D-Assisted Self-Supervised Learning Authors:Xiaoguang Tu, Jian Zhao, Zihang Jiang, Yao Luo, Mei Xie, Yang Zhao, Linxiao He, Zheng Ma, Jiashi Feng

8.Title: Overcoming Small Minirhizotron Datasets Using Transfer Learning Authors:Weihuang Xu, Guohao Yu, Alina Zare, Brendan Zurweller, Diane Rowland, Joel Reyes-Cabrera, Felix B Fritschi, Roser Matamala, Thomas E. Juenger

9.Title: Pose Estimation of Periacetabular Osteotomy Fragments with Intraoperative X-Ray Navigation Authors:Robert B. Grupp, Rachel A. Hegeman, Ryan J. Murphy, Clayton P. Alexander, Yoshito Otake, Benjamin A. McArthur, Mehran Armand, Russell H. Taylor

10.Title: Unsupervised Deformable Registration for Multi-Modal Images via Disentangled Representations Authors:Chen Qin, Bibo Shi, Rui Liao, Tommaso Mansi, Daniel Rueckert, Ali Kamen

11.Title: A resnet-based universal method for speckle reduction in optical coherence tomography images Authors:Cai Ning, Shi Fei, Hu Dianlin, Chen Yang

12.Title: Towards Optimal Structured CNN Pruning via Generative Adversarial Learning Authors:Shaohui Lin, Rongrong Ji, Chenqian Yan, Baochang Zhang, Liujuan Cao, Qixiang Ye, Feiyue Huang, David Doermann

13.Title: Fast and accurate reconstruction of HARDI using a 1D encoder-decoder convolutional network Authors:Shi Yin, Zhengqiang Zhang, Qinmu Peng, Xinge You

14.Title: Deep Learning with Anatomical Priors: Imitating Enhanced Autoencoders in Latent Space for Improved Pelvic Bone Segmentation in MRI Authors:Duc Duy Pham, Gurbandurdy Dovletov, Sebastian Warwas, Stefan Landgraeber, Marcus Jäger, Josef Pauli

15.Title: CityFlow: A City-Scale Benchmark for Multi-Target Multi-Camera Vehicle Tracking and Re-Identification Authors:Zheng Tang, Milind Naphade, Ming-Yu Liu, Xiaodong Yang, Stan Birchfield, Shuo Wang, Ratnesh Kumar, David Anastasiu, Jenq-Neng Hwang

16.Title: Deep Radiomics for Brain Tumor Detection and Classification from Multi-Sequence MRI Authors:Subhashis Banerjee, Sushmita Mitra, Francesco Masulli, Stefano Rovetta

17.Title: SkelNetOn 2019 Dataset and Challenge on Deep Learning for Geometric Shape Understanding Authors:Ilke Demir, Camilla Hahn, Kathryn Leonard, Geraldine Morin, Dana Rahbani, Athina Panotopoulou, Amelie Fondevilla, Elena Balashova, Bastien Durix, Adam Kortylewski

18.Title: Multi-person Articulated Tracking with Spatial and Temporal Embeddings Authors:Sheng Jin, Wentao Liu, Wanli Ouyang, Chen Qian

19.Title: Semantic Comparison of State-of-the-Art Deep Learning Methods for Image Multi-Label Classification Authors:Adam Kubany, Shimon Ben Ishay, Ruben-sacha Ohayon, Armin Shmilovici, Lior Rokach, Tomer Doitshman

20.Title: Quantitative Depth Quality Assessment of RGBD Cameras At Close Range Using 3D Printed Fixtures Authors:Michele Pratusevich, Jason Chrisos, Shreyas Aditya

21.Title: Sparse2Dense: From direct sparse odometry to dense 3D reconstruction Authors:Jiexiong Tang, John Folkesson, Patric Jensfelt

Papers from arxiv.org

更多精彩请移步主页

---

pic from pixels.com