CNN for Low Level Image Processing. Huanjing Yue

Size: px
Start display at page:

Download "CNN for Low Level Image Processing. Huanjing Yue"

Transcription

1 CNN for Low Level Image Processing Huanjing Yue

2 Deep Learning for Image Restoration General formulation: min Θ L( x, x) s. t. x = F(y; Θ) Loss function Parameters to be learned Key issues The availability of paired training data The design of learning architecture The definition of loss function 2

3 General Pipeline Training phase Test phase The problem Architecture design Prepare training data Input: degraded-latent image sample pairs Output: Trained model Model training Degraded Image Trained deep network Restored image Input: Degraded images Output: Restored images 3

4 Topics Image Super-resolution Image Denoising Image Deraining Image Dehazing 4

5 Image Super-resolution 5

6 Super-resolution via CNN (SRCNN) (input, bicubic interpolation) (feature map of Conv1) (feature map of Conv2) (output) f 9 1(3), f 1 64, f 5 32 Dong, Chao, et al. Image super-resolution using deep convolutional networks." IEEE PAMI 38.2 (2016): (Its conference version published in ECCV 2014) 6

7 SRCNN: example feature maps 7

8 Very deep CNN for SR (VDSR) Training parameters: 3 64 Jiwon Kim, Jung Kwon Lee, and Kyoung Mu Lee. "Accurate image super-resolution using very deep convolutional networks." CVPR,

9 VDSR with and without Residual Learning Performance table (PSNR) for residual and non-residual networks ( Set5 dataset, X2). Residual networks rapidly approach their convergence within 10 epochs

10 Insights of VDSR Residual learning is effective The deeper, the better Single network for multiple scaling factors (Top)Our results using a single network for all scale factors. Super-resolved images over all scales are clean and sharp. (Bottom) Results of Dong et al. (SRCNN) ( 3 model used for all scales). Result images are not visually pleasing. To handle multiple scales, existing methods require multiple networks. 10

11 LapSRN: Laplacian Pyramid SR Network Red arrows indicate convolutional layers. Blue arrows indicate transposed convolutions (upsampling). Green arrows denote element-wise addition operators. 3 64, conv layer depth (d) in each level is 10 for 2, 4 SR, d=5 for 8 SR Lai, Wei-Sheng, et al. "Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution, CVPR,

12 Main points of LapSRN Robust loss function. Speed. LapSRN is much faster than several CNN based SR methods. This is because it does not require the bicubic interpolation as the input. Progressive reconstruction. It generates multiple intermediate SR predictions in one feed-forward pass through progressive reconstruction using the Laplacian pyramid. 12

13 Image Denoising 13

14 DnCNN: Deep Residual Learning Beyond Gaussian Denoising Batch normalization and residual learning are particularly beneficial to Gaussian noise removal Single model for multiple tasks (e.g. super-resolution, deblocking) Training details: 3 64, depth: 17 K. Zhang, W. Zuo, Y. Chen, D. Meng, L. Zhang, "Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising," IEEE Trans. on Image Processing,

15 Effect of Batch Normalization and Residual Learning Learning residual (noise) is easier compared with learning noise free image. 15

16 Gaussian Denoising Results DnCNN-S: DnCNN model trained by specific noise level. DnCNN-B: DnCNN model trained by multiple noise levels, which could be used for blind Gaussian denoising task. 16

17 Connecting model based optimization and discriminative learning based methods Model based optimization methods General to handle different image restoration problems The hand-crafted prior may not be strong enough Discriminative learning based methods Data driven end-to-end learning The generality of learned models is limited Can we integrate the model based optimization and discriminative learning to develop a general image restoration method? 17

18 Half quadratic splitting 18

19 Image restoration with deep CNN denoiser prior (IRCNN) Plugging the strong CNN denoiser prior into model based optimization Step (a): analytical solution Step (b): deep CNN denoiser K. Zhang, W. Zuo, S. Gu, L. Zhang. "Learning Deep CNN Denoiser Prior for Image Restoration." CVPR

20 CNN Denoiser s-dconv denotes s-dilated convolution, s = 1, 2, 3 and 4. A dilated filter with dilation factor s can be simply interpreted as a sparse filter of size (2s+1) (2s+1) where only 9 entries of fixed positions are non-zeros. 20

21 Experiment Results 21

22 Problem: ADMM solution: Cnn solution: DeepAM: Deeply Aggregated Alternating Minimization for Image Restoration (CVPR 2017) 22

23 DeepAM: Deeply Aggregated Alternating Minimization for Image Restoration (CVPR 2017) 23

24 Image Deraining 24

25 Deep Joint Rain Detection and Removal from a Single Image (CVPR 2017) 25

26 Results DSC: Y.Luo,Y.Xu,andH.Ji. Removing rain from a single image via discriminative sparse coding. ICCV LP: Y. Li, R. T. Tan, X. Guo, J. Lu, and M. S. Brown. Rain streak removal using layer priors. CVPR

27 Removing rain from single images via a deep detail network. CVPR DSC LP 27

28 Image Dehazing 28

29 Single Image Dehazing via Multi-Scale Convolutional Neural Networks (ECCV 2016) Wenqi Ren et al. Single Image Dehazing via Multi-Scale Convolutional Neural Networks, ECCV

30 Results 30

31 Open Problems Taking advantage of the classical image restoration methods and applying them to the CNN based restoration. For problems without training-pairs available. e.g. realistic noise removal, underwater image enhancement. Use GAN? Exploring more flexible and light network structures with less parameters to be trained. 31

32 Thanks! References: Lei Zhang, Image Restoration: From Sparse and Low-rank Priors to Deep Priors. 32

33 Convolution Layer 33

34 Convolution Layer 34

35 Convolution Layer 35

36 Pooling Layer 36

37 Non-linear Activation 37

38 Batch Normalization 38

39 Loss Function 39 Softmax Softmax Loss

40 Questions The rules for designing neural network architecture. Generally, the NN architecture with wider and deeper structure could generate better results. Right? If one NN works well on current problem, could we improve its performance by introducing more parameters, for example, densely connection, make it wider or deeper, introducing some skip connections? The common strategy used for designing NN structure. 40

41 41

Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform. Xintao Wang Ke Yu Chao Dong Chen Change Loy

Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform. Xintao Wang Ke Yu Chao Dong Chen Change Loy Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform Xintao Wang Ke Yu Chao Dong Chen Change Loy Problem enlarge 4 times Low-resolution image High-resolution image Previous

More information

RTSR: Enhancing Real-time H.264 Video Streaming using Deep Learning based Video Super Resolution Spring 2017 CS570 Project Presentation June 8, 2017

RTSR: Enhancing Real-time H.264 Video Streaming using Deep Learning based Video Super Resolution Spring 2017 CS570 Project Presentation June 8, 2017 RTSR: Enhancing Real-time H.264 Video Streaming using Deep Learning based Video Super Resolution Spring 2017 CS570 Project Presentation June 8, 2017 Team 16 Soomin Kim Leslie Tiong Youngki Kwon Insu Jang

More information

Efficient Module Based Single Image Super Resolution for Multiple Problems

Efficient Module Based Single Image Super Resolution for Multiple Problems Efficient Module Based Single Image Super Resolution for Multiple Problems Dongwon Park Kwanyoung Kim Se Young Chun School of ECE, Ulsan National Institute of Science and Technology, 44919, Ulsan, South

More information

SINGLE image super-resolution (SR) aims to reconstruct

SINGLE image super-resolution (SR) aims to reconstruct Fast and Accurate Image Super-Resolution with Deep Laplacian Pyramid Networks Wei-Sheng Lai, Jia-Bin Huang, Narendra Ahuja, and Ming-Hsuan Yang 1 arxiv:1710.01992v3 [cs.cv] 9 Aug 2018 Abstract Convolutional

More information

One Network to Solve Them All Solving Linear Inverse Problems using Deep Projection Models

One Network to Solve Them All Solving Linear Inverse Problems using Deep Projection Models One Network to Solve Them All Solving Linear Inverse Problems using Deep Projection Models [Supplemental Materials] 1. Network Architecture b ref b ref +1 We now describe the architecture of the networks

More information

Image Restoration: From Sparse and Low-rank Priors to Deep Priors

Image Restoration: From Sparse and Low-rank Priors to Deep Priors Image Restoration: From Sparse and Low-rank Priors to Deep Priors Lei Zhang 1, Wangmeng Zuo 2 1 Dept. of computing, The Hong Kong Polytechnic University, 2 School of Computer Science and Technology, Harbin

More information

Deep Back-Projection Networks For Super-Resolution Supplementary Material

Deep Back-Projection Networks For Super-Resolution Supplementary Material Deep Back-Projection Networks For Super-Resolution Supplementary Material Muhammad Haris 1, Greg Shakhnarovich 2, and Norimichi Ukita 1, 1 Toyota Technological Institute, Japan 2 Toyota Technological Institute

More information

SINGLE image super-resolution (SR) aims to reconstruct

SINGLE image super-resolution (SR) aims to reconstruct Fast and Accurate Image Super-Resolution with Deep Laplacian Pyramid Networks Wei-Sheng Lai, Jia-Bin Huang, Narendra Ahuja, and Ming-Hsuan Yang 1 arxiv:1710.01992v2 [cs.cv] 11 Oct 2017 Abstract Convolutional

More information

Single Image Super Resolution of Textures via CNNs. Andrew Palmer

Single Image Super Resolution of Textures via CNNs. Andrew Palmer Single Image Super Resolution of Textures via CNNs Andrew Palmer What is Super Resolution (SR)? Simple: Obtain one or more high-resolution images from one or more low-resolution ones Many, many applications

More information

Accelerated very deep denoising convolutional neural network for image super-resolution NTIRE2017 factsheet

Accelerated very deep denoising convolutional neural network for image super-resolution NTIRE2017 factsheet Accelerated very deep denoising convolutional neural network for image super-resolution NTIRE2017 factsheet Yunjin Chen, Kai Zhang and Wangmeng Zuo April 17, 2017 1 Team details Team name HIT-ULSee Team

More information

FAST: A Framework to Accelerate Super- Resolution Processing on Compressed Videos

FAST: A Framework to Accelerate Super- Resolution Processing on Compressed Videos FAST: A Framework to Accelerate Super- Resolution Processing on Compressed Videos Zhengdong Zhang, Vivienne Sze Massachusetts Institute of Technology http://www.mit.edu/~sze/fast.html 1 Super-Resolution

More information

Infrared Image Enhancement in Maritime Environment with Convolutional Neural Networks

Infrared Image Enhancement in Maritime Environment with Convolutional Neural Networks Infrared Image Enhancement in Maritime Environment with Convolutional Neural Networks Purbaditya Bhattacharya1, Jo rg Riechen2 and Udo Zo lzer1 1 Department 2 WTD of Signal Processing and Communications,

More information

DCGANs for image super-resolution, denoising and debluring

DCGANs for image super-resolution, denoising and debluring DCGANs for image super-resolution, denoising and debluring Qiaojing Yan Stanford University Electrical Engineering qiaojing@stanford.edu Wei Wang Stanford University Electrical Engineering wwang23@stanford.edu

More information

SINGLE image restoration (IR) aims to generate a visually

SINGLE image restoration (IR) aims to generate a visually Concat 1x1 JOURNAL OF L A T E X CLASS FILES, VOL. 13, NO. 9, SEPTEMBER 2014 1 Residual Dense Network for Image Restoration Yulun Zhang, Yapeng Tian, Yu Kong, Bineng Zhong, and Yun Fu, Fellow, IEEE arxiv:1812.10477v1

More information

arxiv: v2 [cs.cv] 11 Nov 2016

arxiv: v2 [cs.cv] 11 Nov 2016 Accurate Image Super-Resolution Using Very Deep Convolutional Networks Jiwon Kim, Jung Kwon Lee and Kyoung Mu Lee Department of ECE, ASRI, Seoul National University, Korea {j.kim, deruci, kyoungmu}@snu.ac.kr

More information

Introduction. Prior work BYNET: IMAGE SUPER RESOLUTION WITH A BYPASS CONNECTION NETWORK. Bjo rn Stenger. Rakuten Institute of Technology

Introduction. Prior work BYNET: IMAGE SUPER RESOLUTION WITH A BYPASS CONNECTION NETWORK. Bjo rn Stenger. Rakuten Institute of Technology BYNET: IMAGE SUPER RESOLUTION WITH A BYPASS CONNECTION NETWORK Jiu Xu Yeongnam Chae Bjo rn Stenger Rakuten Institute of Technology ABSTRACT This paper proposes a deep residual network, ByNet, for the single

More information

arxiv: v1 [cs.cv] 7 Aug 2017

arxiv: v1 [cs.cv] 7 Aug 2017 MemNet: A Persistent Memory Network for Image Restoration Ying Tai 1, Jian Yang 1, Xiaoming Liu 2, and Chunyan Xu 1 1 Department of Computer Science and Engineering, Nanjing University of Science and Technology

More information

Image Restoration with Deep Generative Models

Image Restoration with Deep Generative Models Image Restoration with Deep Generative Models Raymond A. Yeh *, Teck-Yian Lim *, Chen Chen, Alexander G. Schwing, Mark Hasegawa-Johnson, Minh N. Do Department of Electrical and Computer Engineering, University

More information

Bidirectional Recurrent Convolutional Networks for Video Super-Resolution

Bidirectional Recurrent Convolutional Networks for Video Super-Resolution Bidirectional Recurrent Convolutional Networks for Video Super-Resolution Qi Zhang & Yan Huang Center for Research on Intelligent Perception and Computing (CRIPAC) National Laboratory of Pattern Recognition

More information

Removing rain from single images via a deep detail network

Removing rain from single images via a deep detail network 207 IEEE Conference on Computer Vision and Pattern Recognition Removing rain from single images via a deep detail network Xueyang Fu Jiabin Huang Delu Zeng 2 Yue Huang Xinghao Ding John Paisley 3 Key Laboratory

More information

Removing rain from single images via a deep detail network

Removing rain from single images via a deep detail network Removing rain from single images via a deep detail network Xueyang Fu 1 Jiabin Huang 1 Delu Zeng 2 Yue Huang 1 Xinghao Ding 1 John Paisley 3 1 Key Laboratory of Underwater Acoustic Communication and Marine

More information

DENSE BYNET: RESIDUAL DENSE NETWORK FOR IMAGE SUPER RESOLUTION. Bjo rn Stenger2

DENSE BYNET: RESIDUAL DENSE NETWORK FOR IMAGE SUPER RESOLUTION. Bjo rn Stenger2 DENSE BYNET: RESIDUAL DENSE NETWORK FOR IMAGE SUPER RESOLUTION Jiu Xu1 Yeongnam Chae2 1 Bjo rn Stenger2 Ankur Datta1 Rakuten Institute of Technology, Boston Rakuten Institute of Technology, Tokyo 2 ABSTRACT

More information

Lecture 7: Semantic Segmentation

Lecture 7: Semantic Segmentation Semantic Segmentation CSED703R: Deep Learning for Visual Recognition (207F) Segmenting images based on its semantic notion Lecture 7: Semantic Segmentation Bohyung Han Computer Vision Lab. bhhanpostech.ac.kr

More information

UDNet: Up-Down Network for Compact and Efficient Feature Representation in Image Super-Resolution

UDNet: Up-Down Network for Compact and Efficient Feature Representation in Image Super-Resolution UDNet: Up-Down Network for Compact and Efficient Feature Representation in Image Super-Resolution Chang Chen Xinmei Tian Zhiwei Xiong Feng Wu University of Science and Technology of China Abstract Recently,

More information

Deep Boosting for Image Denoising

Deep Boosting for Image Denoising Deep Boosting for Image Denoising Chang Chen, Zhiwei Xiong ( ), Xinmei Tian, and Feng Wu University of Science and Technology of China changc@mail.ustc.edu.cn, {zwxiong,xinmei,fengwu}@ustc.edu.cn Abstract.

More information

DPW-SDNet: Dual Pixel-Wavelet Domain Deep CNNs for Soft Decoding of JPEG-Compressed Images

DPW-SDNet: Dual Pixel-Wavelet Domain Deep CNNs for Soft Decoding of JPEG-Compressed Images DPW-SDNet: Dual Pixel-Wavelet Domain Deep CNNs for Soft Decoding of JPEG-Compressed Images Honggang Chen Sichuan University honggang chen@yeah.net Shuhua Xiong Sichuan University xiongsh@scu.edu.cn Xiaohai

More information

Fast and Accurate Single Image Super-Resolution via Information Distillation Network

Fast and Accurate Single Image Super-Resolution via Information Distillation Network Fast and Accurate Single Image Super-Resolution via Information Distillation Network Recently, due to the strength of deep convolutional neural network (CNN), many CNN-based SR methods try to train a deep

More information

ECE 484 Digital Image Processing Lec 17 - Part II Review & Final Projects Topics

ECE 484 Digital Image Processing Lec 17 - Part II Review & Final Projects Topics ECE 484 Digital Image Processing Lec 17 - Part II Review & Final Projects opics Zhu Li Dept of CSEE, UMKC Office: FH560E, Email: lizhu@umkc.edu, Ph: x 2346. http://l.web.umkc.edu/lizhu slides created with

More information

Residual Dense Network for Image Super-Resolution

Residual Dense Network for Image Super-Resolution Residual Dense Network for Image Super-Resolution Yulun Zhang 1, Yapeng Tian 2,YuKong 1, Bineng Zhong 1, Yun Fu 1,3 1 Department of Electrical and Computer Engineering, Northeastern University, Boston,

More information

Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform Supplementary Material

Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform Supplementary Material Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform Supplementary Material Xintao Wang 1 Ke Yu 1 Chao Dong 2 Chen Change Loy 1 1 CUHK - SenseTime Joint Lab, The Chinese

More information

arxiv: v1 [cs.cv] 29 Jul 2018

arxiv: v1 [cs.cv] 29 Jul 2018 arxiv:1807.11078v1 [cs.cv] 29 Jul 2018 Semi-supervised CNN for Single Image Rain Removal Wei Wei, Deyu Meng, Qian Zhao and Zongben Xu School of Mathematics and Statistics, Xi an Jiaotong University weiweiwe@stu.mail.xjtu.edu.cn,

More information

arxiv: v1 [cs.cv] 8 Feb 2018

arxiv: v1 [cs.cv] 8 Feb 2018 DEEP IMAGE SUPER RESOLUTION VIA NATURAL IMAGE PRIORS Hojjat S. Mousavi, Tiantong Guo, Vishal Monga Dept. of Electrical Engineering, The Pennsylvania State University arxiv:802.0272v [cs.cv] 8 Feb 208 ABSTRACT

More information

Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution

Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution Wei-Sheng Lai 1 Jia-Bin Huang 2 Narendra Ahuja 3 Ming-Hsuan Yang 1 1 University of California, Merced 2 Virginia Tech 3 University

More information

arxiv: v1 [cs.cv] 18 Dec 2018 Abstract

arxiv: v1 [cs.cv] 18 Dec 2018 Abstract SREdgeNet: Edge Enhanced Single Image Super Resolution using Dense Edge Detection Network and Feature Merge Network Kwanyoung Kim, Se Young Chun Ulsan National Institute of Science and Technology (UNIST),

More information

Physics-Based Generative Adversarial Models for Image Restoration and Beyond

Physics-Based Generative Adversarial Models for Image Restoration and Beyond 1 Physics-Based Generative Adversarial Models for Image Restoration and Beyond Jinshan Pan, Yang Liu, Jiangxin Dong, Jiawei Zhang, Jimmy Ren, Jinhui Tang, Yu-Wing Tai and Ming-Hsuan Yang arxiv:1808.00605v1

More information

Deep learning for dense per-pixel prediction. Chunhua Shen The University of Adelaide, Australia

Deep learning for dense per-pixel prediction. Chunhua Shen The University of Adelaide, Australia Deep learning for dense per-pixel prediction Chunhua Shen The University of Adelaide, Australia Image understanding Classification error Convolution Neural Networks 0.3 0.2 0.1 Image Classification [Krizhevsky

More information

EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis Supplementary

EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis Supplementary EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis Supplementary Mehdi S. M. Sajjadi Bernhard Schölkopf Michael Hirsch Max Planck Institute for Intelligent Systems Spemanstr.

More information

Learning a Single Convolutional Super-Resolution Network for Multiple Degradations

Learning a Single Convolutional Super-Resolution Network for Multiple Degradations Learning a Single Convolutional Super-Resolution Network for Multiple Degradations Kai Zhang,2, Wangmeng Zuo, Lei Zhang 2 School of Computer Science and Technology, Harbin Institute of Technology, Harbin,

More information

arxiv: v1 [cs.cv] 31 Dec 2018 Abstract

arxiv: v1 [cs.cv] 31 Dec 2018 Abstract Image Super-Resolution via RL-CSC: When Residual Learning Meets olutional Sparse Coding Menglei Zhang, Zhou Liu, Lei Yu School of Electronic and Information, Wuhan University, China {zmlhome, liuzhou,

More information

Structured Prediction using Convolutional Neural Networks

Structured Prediction using Convolutional Neural Networks Overview Structured Prediction using Convolutional Neural Networks Bohyung Han bhhan@postech.ac.kr Computer Vision Lab. Convolutional Neural Networks (CNNs) Structured predictions for low level computer

More information

SINGLE image super-resolution (SR) aims to infer a high. Single Image Super-Resolution via Cascaded Multi-Scale Cross Network

SINGLE image super-resolution (SR) aims to infer a high. Single Image Super-Resolution via Cascaded Multi-Scale Cross Network This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible. 1 Single Image Super-Resolution via

More information

Image Super-Resolution Using Dense Skip Connections

Image Super-Resolution Using Dense Skip Connections Image Super-Resolution Using Dense Skip Connections Tong Tong, Gen Li, Xiejie Liu, Qinquan Gao Imperial Vision Technology Fuzhou, China {ttraveltong,ligen,liu.xiejie,gqinquan}@imperial-vision.com Abstract

More information

A Novel Multi-Frame Color Images Super-Resolution Framework based on Deep Convolutional Neural Network. Zhe Li, Shu Li, Jianmin Wang and Hongyang Wang

A Novel Multi-Frame Color Images Super-Resolution Framework based on Deep Convolutional Neural Network. Zhe Li, Shu Li, Jianmin Wang and Hongyang Wang 5th International Conference on Measurement, Instrumentation and Automation (ICMIA 2016) A Novel Multi-Frame Color Images Super-Resolution Framewor based on Deep Convolutional Neural Networ Zhe Li, Shu

More information

arxiv: v1 [cs.cv] 5 Jul 2017

arxiv: v1 [cs.cv] 5 Jul 2017 AlignGAN: Learning to Align Cross- Images with Conditional Generative Adversarial Networks Xudong Mao Department of Computer Science City University of Hong Kong xudonmao@gmail.com Qing Li Department of

More information

DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution and Fully Connected CRFs

DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution and Fully Connected CRFs DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution and Fully Connected CRFs Zhipeng Yan, Moyuan Huang, Hao Jiang 5/1/2017 1 Outline Background semantic segmentation Objective,

More information

arxiv: v2 [cs.cv] 24 May 2018

arxiv: v2 [cs.cv] 24 May 2018 Learning a Single Convolutional Super-Resolution Network for Multiple Degradations Kai Zhang 1,2,3, Wangmeng Zuo 1, Lei Zhang 2 1 School of Computer Science and Technology, Harbin Institute of Technology,

More information

SSD: Single Shot MultiBox Detector. Author: Wei Liu et al. Presenter: Siyu Jiang

SSD: Single Shot MultiBox Detector. Author: Wei Liu et al. Presenter: Siyu Jiang SSD: Single Shot MultiBox Detector Author: Wei Liu et al. Presenter: Siyu Jiang Outline 1. Motivations 2. Contributions 3. Methodology 4. Experiments 5. Conclusions 6. Extensions Motivation Motivation

More information

arxiv: v1 [cs.cv] 21 Dec 2018

arxiv: v1 [cs.cv] 21 Dec 2018 A Multiscale Image Denoising Algorithm Based On Dilated Residual Convolution Network arxiv:1812.09131v1 [cs.cv] 21 Dec 2018 Chang Liu College of Computer Science Chongqing University Chongqing, China Email:

More information

arxiv: v1 [cs.cv] 21 Nov 2018

arxiv: v1 [cs.cv] 21 Nov 2018 A Deep Tree-Structured Fusion Model for Single Image Deraining Xueyang Fu, Qi Qi, Yue Huang, Xinghao Ding, Feng Wu, John Paisley School of Information Science and Technology, Xiamen University, China School

More information

Multilayer and Multimodal Fusion of Deep Neural Networks for Video Classification

Multilayer and Multimodal Fusion of Deep Neural Networks for Video Classification Multilayer and Multimodal Fusion of Deep Neural Networks for Video Classification Xiaodong Yang, Pavlo Molchanov, Jan Kautz INTELLIGENT VIDEO ANALYTICS Surveillance event detection Human-computer interaction

More information

Fast Guided Global Interpolation for Depth and. Yu Li, Dongbo Min, Minh N. Do, Jiangbo Lu

Fast Guided Global Interpolation for Depth and. Yu Li, Dongbo Min, Minh N. Do, Jiangbo Lu Fast Guided Global Interpolation for Depth and Yu Li, Dongbo Min, Minh N. Do, Jiangbo Lu Introduction Depth upsampling and motion interpolation are often required to generate a dense, high-quality, and

More information

with Deep Learning A Review of Person Re-identification Xi Li College of Computer Science, Zhejiang University

with Deep Learning A Review of Person Re-identification Xi Li College of Computer Science, Zhejiang University A Review of Person Re-identification with Deep Learning Xi Li College of Computer Science, Zhejiang University http://mypage.zju.edu.cn/xilics Email: xilizju@zju.edu.cn Person Re-identification Associate

More information

Light Field Super Resolution with Convolutional Neural Networks

Light Field Super Resolution with Convolutional Neural Networks Light Field Super Resolution with Convolutional Neural Networks by Andrew Hou A Thesis submitted in partial fulfillment of the requirements for Honors in the Department of Applied Mathematics and Computer

More information

arxiv: v2 [cs.cv] 1 Sep 2016

arxiv: v2 [cs.cv] 1 Sep 2016 Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections arxiv:1603.09056v2 [cs.cv] 1 Sep 2016 Xiao-Jiao Mao, Chunhua Shen, Yu-Bin Yang State Key Laboratory

More information

arxiv: v1 [cs.cv] 25 Dec 2017

arxiv: v1 [cs.cv] 25 Dec 2017 Deep Blind Image Inpainting Yang Liu 1, Jinshan Pan 2, Zhixun Su 1 1 School of Mathematical Sciences, Dalian University of Technology 2 School of Computer Science and Engineering, Nanjing University of

More information

Learning Fully Convolutional Networks for Iterative Non-blind Deconvolution

Learning Fully Convolutional Networks for Iterative Non-blind Deconvolution Learning Fully Convolutional Networks for Iterative Non-blind Deconvolution Jiawei Zhang 13 Jinshan Pan 2 Wei-Sheng Lai 3 Rynson W.H. Lau 1 Ming-Hsuan Yang 3 Department of Computer Science, City University

More information

arxiv: v2 [cs.cv] 19 Apr 2019

arxiv: v2 [cs.cv] 19 Apr 2019 arxiv:1809.04789v2 [cs.cv] 19 Apr 2019 Deep Learning-based Image Super-Resolution Considering Quantitative and Perceptual Quality Jun-Ho Choi, Jun-Hyuk Kim, Manri Cheon, and Jong-Seok Lee School of Integrated

More information

Example-Based Image Super-Resolution Techniques

Example-Based Image Super-Resolution Techniques Example-Based Image Super-Resolution Techniques Mark Sabini msabini & Gili Rusak gili December 17, 2016 1 Introduction With the current surge in popularity of imagebased applications, improving content

More information

Lab meeting (Paper review session) Stacked Generative Adversarial Networks

Lab meeting (Paper review session) Stacked Generative Adversarial Networks Lab meeting (Paper review session) Stacked Generative Adversarial Networks 2017. 02. 01. Saehoon Kim (Ph. D. candidate) Machine Learning Group Papers to be covered Stacked Generative Adversarial Networks

More information

Multi-Input Cardiac Image Super-Resolution using Convolutional Neural Networks

Multi-Input Cardiac Image Super-Resolution using Convolutional Neural Networks Multi-Input Cardiac Image Super-Resolution using Convolutional Neural Networks Ozan Oktay, Wenjia Bai, Matthew Lee, Ricardo Guerrero, Konstantinos Kamnitsas, Jose Caballero, Antonio de Marvao, Stuart Cook,

More information

AdaDepth: Unsupervised Content Congruent Adaptation for Depth Estimation

AdaDepth: Unsupervised Content Congruent Adaptation for Depth Estimation AdaDepth: Unsupervised Content Congruent Adaptation for Depth Estimation Introduction Supplementary material In the supplementary material, we present additional qualitative results of the proposed AdaDepth

More information

Residual Networks And Attention Models. cs273b Recitation 11/11/2016. Anna Shcherbina

Residual Networks And Attention Models. cs273b Recitation 11/11/2016. Anna Shcherbina Residual Networks And Attention Models cs273b Recitation 11/11/2016 Anna Shcherbina Introduction to ResNets Introduced in 2015 by Microsoft Research Deep Residual Learning for Image Recognition (He, Zhang,

More information

POINT CLOUD DEEP LEARNING

POINT CLOUD DEEP LEARNING POINT CLOUD DEEP LEARNING Innfarn Yoo, 3/29/28 / 57 Introduction AGENDA Previous Work Method Result Conclusion 2 / 57 INTRODUCTION 3 / 57 2D OBJECT CLASSIFICATION Deep Learning for 2D Object Classification

More information

arxiv: v1 [cs.cv] 29 Sep 2016

arxiv: v1 [cs.cv] 29 Sep 2016 arxiv:1609.09545v1 [cs.cv] 29 Sep 2016 Two-stage Convolutional Part Heatmap Regression for the 1st 3D Face Alignment in the Wild (3DFAW) Challenge Adrian Bulat and Georgios Tzimiropoulos Computer Vision

More information

GAN-D: Generative Adversarial Networks for Image Deconvolution

GAN-D: Generative Adversarial Networks for Image Deconvolution GAN-D: Generative Adversarial Networks for Image Deconvolution Ha Yeon Lee, Jin Myung Kwak, Byunghyun Ban, Seon Jin Na, Se Ra Lee, Heung-Kyu Lee School of Computing and Department of Bio and Brain Engineering

More information

arxiv: v1 [cs.cv] 20 Dec 2016

arxiv: v1 [cs.cv] 20 Dec 2016 End-to-End Pedestrian Collision Warning System based on a Convolutional Neural Network with Semantic Segmentation arxiv:1612.06558v1 [cs.cv] 20 Dec 2016 Heechul Jung heechul@dgist.ac.kr Min-Kook Choi mkchoi@dgist.ac.kr

More information

CARN: Convolutional Anchored Regression Network for Fast and Accurate Single Image Super-Resolution

CARN: Convolutional Anchored Regression Network for Fast and Accurate Single Image Super-Resolution CARN: Convolutional Anchored Regression Network for Fast and Accurate Single Image Super-Resolution Yawei Li 1, Eirikur Agustsson 1, Shuhang Gu 1, Radu Timofte 1, and Luc Van Gool 1,2 1 ETH Zürich, Sternwartstrasse

More information

Towards Weakly- and Semi- Supervised Object Localization and Semantic Segmentation

Towards Weakly- and Semi- Supervised Object Localization and Semantic Segmentation Towards Weakly- and Semi- Supervised Object Localization and Semantic Segmentation Lecturer: Yunchao Wei Image Formation and Processing (IFP) Group University of Illinois at Urbanahttps://weiyc.githu Champaign

More information

Deblurring Text Images via L 0 -Regularized Intensity and Gradient Prior

Deblurring Text Images via L 0 -Regularized Intensity and Gradient Prior Deblurring Text Images via L -Regularized Intensity and Gradient Prior Jinshan Pan, Zhe Hu, Zhixun Su, Ming-Hsuan Yang School of Mathematical Sciences, Dalian University of Technology Electrical Engineering

More information

Deep learning for object detection. Slides from Svetlana Lazebnik and many others

Deep learning for object detection. Slides from Svetlana Lazebnik and many others Deep learning for object detection Slides from Svetlana Lazebnik and many others Recent developments in object detection 80% PASCAL VOC mean0average0precision0(map) 70% 60% 50% 40% 30% 20% 10% Before deep

More information

Computer Vision Lecture 16

Computer Vision Lecture 16 Computer Vision Lecture 16 Deep Learning Applications 11.01.2017 Bastian Leibe RWTH Aachen http://www.vision.rwth-aachen.de leibe@vision.rwth-aachen.de Announcements Seminar registration period starts

More information

Image Super Resolution Based on Fusing Multiple Convolution Neural Networks

Image Super Resolution Based on Fusing Multiple Convolution Neural Networks Image Super Resolution Based on Fusing Multiple Convolution Neural Networks Haoyu Ren, Mostafa El-Khamy, Jungwon Lee SAMSUNG SEMICONDUCTOR INC. 4921 Directors Place, San Diego, CA, US {haoyu.ren, mostafa.e,

More information

Fast and Accurate Image Super-Resolution Using A Combined Loss

Fast and Accurate Image Super-Resolution Using A Combined Loss Fast and Accurate Image Super-Resolution Using A Combined Loss Jinchang Xu 1, Yu Zhao 1, Yuan Dong 1, Hongliang Bai 2 1 Beijing University of Posts and Telecommunications, 2 Beijing Faceall Technology

More information

Video Object Segmentation using Deep Learning

Video Object Segmentation using Deep Learning Video Object Segmentation using Deep Learning Update Presentation, Week 3 Zack While Advised by: Rui Hou, Dr. Chen Chen, and Dr. Mubarak Shah June 2, 2017 Youngstown State University 1 Table of Contents

More information

Blind Image Deblurring Using Dark Channel Prior

Blind Image Deblurring Using Dark Channel Prior Blind Image Deblurring Using Dark Channel Prior Jinshan Pan 1,2,3, Deqing Sun 2,4, Hanspeter Pfister 2, and Ming-Hsuan Yang 3 1 Dalian University of Technology 2 Harvard University 3 UC Merced 4 NVIDIA

More information

Progress on Generative Adversarial Networks

Progress on Generative Adversarial Networks Progress on Generative Adversarial Networks Wangmeng Zuo Vision Perception and Cognition Centre Harbin Institute of Technology Content Image generation: problem formulation Three issues about GAN Discriminate

More information

Quality Enhancement of Compressed Video via CNNs

Quality Enhancement of Compressed Video via CNNs Journal of Information Hiding and Multimedia Signal Processing c 2017 ISSN 2073-4212 Ubiquitous International Volume 8, Number 1, January 2017 Quality Enhancement of Compressed Video via CNNs Jingxuan

More information

OPTICAL Character Recognition systems aim at converting

OPTICAL Character Recognition systems aim at converting ICDAR 2015 COMPETITION ON TEXT IMAGE SUPER-RESOLUTION 1 Boosting Optical Character Recognition: A Super-Resolution Approach Chao Dong, Ximei Zhu, Yubin Deng, Chen Change Loy, Member, IEEE, and Yu Qiao

More information

Fast and Accurate Single Image Super-Resolution via Information Distillation Network

Fast and Accurate Single Image Super-Resolution via Information Distillation Network Fast and Accurate Single Image Super-Resolution via Information Distillation Network Zheng Hui, Xiumei Wang, Xinbo Gao School of Electronic Engineering, Xidian University Xi an, China zheng hui@aliyun.com,

More information

arxiv: v1 [cs.cv] 30 Nov 2018

arxiv: v1 [cs.cv] 30 Nov 2018 Super-Resolution based on Image-Adapted CNN Denoisers: Incorporating Generalization of Training Data and Internal Learning in Test Time arxiv:1811.12866v1 [cs.cv] 30 Nov 2018 Tom Tirer Tel Aviv University,

More information

Multi-scale Residual Network for Image Super-Resolution

Multi-scale Residual Network for Image Super-Resolution Multi-scale Residual Network for Image Super-Resolution Juncheng Li 1[0000 0001 7314 6754], Faming Fang 1[0000 0003 4511 4813], Kangfu Mei 2[0000 0001 8949 9597], and Guixu Zhang 1[0000 0003 4720 6607]

More information

Unsupervised Learning

Unsupervised Learning Deep Learning for Graphics Unsupervised Learning Niloy Mitra Iasonas Kokkinos Paul Guerrero Vladimir Kim Kostas Rematas Tobias Ritschel UCL UCL/Facebook UCL Adobe Research U Washington UCL Timetable Niloy

More information

ECCV Presented by: Boris Ivanovic and Yolanda Wang CS 331B - November 16, 2016

ECCV Presented by: Boris Ivanovic and Yolanda Wang CS 331B - November 16, 2016 ECCV 2016 Presented by: Boris Ivanovic and Yolanda Wang CS 331B - November 16, 2016 Fundamental Question What is a good vector representation of an object? Something that can be easily predicted from 2D

More information

Research Faculty Summit Systems Fueling future disruptions

Research Faculty Summit Systems Fueling future disruptions Research Faculty Summit 2018 Systems Fueling future disruptions Efficient Edge Computing for Deep Neural Networks and Beyond Vivienne Sze In collaboration with Yu-Hsin Chen, Joel Emer, Tien-Ju Yang, Sertac

More information

Generative Modeling with Convolutional Neural Networks. Denis Dus Data Scientist at InData Labs

Generative Modeling with Convolutional Neural Networks. Denis Dus Data Scientist at InData Labs Generative Modeling with Convolutional Neural Networks Denis Dus Data Scientist at InData Labs What we will discuss 1. 2. 3. 4. Discriminative vs Generative modeling Convolutional Neural Networks How to

More information

JOINT DETECTION AND SEGMENTATION WITH DEEP HIERARCHICAL NETWORKS. Zhao Chen Machine Learning Intern, NVIDIA

JOINT DETECTION AND SEGMENTATION WITH DEEP HIERARCHICAL NETWORKS. Zhao Chen Machine Learning Intern, NVIDIA JOINT DETECTION AND SEGMENTATION WITH DEEP HIERARCHICAL NETWORKS Zhao Chen Machine Learning Intern, NVIDIA ABOUT ME 5th year PhD student in physics @ Stanford by day, deep learning computer vision scientist

More information

A DEEP DICTIONARY MODEL FOR IMAGE SUPER-RESOLUTION. Jun-Jie Huang and Pier Luigi Dragotti

A DEEP DICTIONARY MODEL FOR IMAGE SUPER-RESOLUTION. Jun-Jie Huang and Pier Luigi Dragotti A DEEP DICTIONARY MODEL FOR IMAGE SUPER-RESOLUTION Jun-Jie Huang and Pier Luigi Dragotti Communications and Signal Processing Group CSP), Imperial College London, UK ABSTRACT Inspired by the recent success

More information

Deep Learning and Its Applications

Deep Learning and Its Applications Convolutional Neural Network and Its Application in Image Recognition Oct 28, 2016 Outline 1 A Motivating Example 2 The Convolutional Neural Network (CNN) Model 3 Training the CNN Model 4 Issues and Recent

More information

Flow-Based Video Recognition

Flow-Based Video Recognition Flow-Based Video Recognition Jifeng Dai Visual Computing Group, Microsoft Research Asia Joint work with Xizhou Zhu*, Yuwen Xiong*, Yujie Wang*, Lu Yuan and Yichen Wei (* interns) Talk pipeline Introduction

More information

An Effective Single-Image Super-Resolution Model Using Squeeze-and-Excitation Networks

An Effective Single-Image Super-Resolution Model Using Squeeze-and-Excitation Networks An Effective Single-Image Super-Resolution Model Using Squeeze-and-Excitation Networks Kangfu Mei 1, Juncheng Li 2, Luyao 1, Mingwen Wang 1, Aiwen Jiang 1 Jiangxi Normal University 1 East China Normal

More information

Computer Vision Lecture 16

Computer Vision Lecture 16 Announcements Computer Vision Lecture 16 Deep Learning Applications 11.01.2017 Seminar registration period starts on Friday We will offer a lab course in the summer semester Deep Robot Learning Topic:

More information

xunit: Learning a Spatial Activation Function for Efficient Image Restoration

xunit: Learning a Spatial Activation Function for Efficient Image Restoration xunit: Learning a Spatial Activation Function for Efficient Image Restoration Idan Kligvasser, Tamar Rott Shaham and Tomer Michaeli Technion Israel Institute of Technology, Haifa, Israel {kligvasser@campus,stamarot@campus,tomer.m@ee}.technion.ac.il

More information

Deep CNN Denoiser and Multi-layer Neighbor Component Embedding for Face Hallucination

Deep CNN Denoiser and Multi-layer Neighbor Component Embedding for Face Hallucination Deep CNN Denoiser and Multi-layer Neighbor Component Embedding for Face Hallucination Junjun Jiang 1,2, Yi Yu 2, Jinhui Hu 3, Suhua Tang 4 and Jiayi Ma 5 1 Harbin Institute of Technology, Harbin, China

More information

Image Restoration Using DNN

Image Restoration Using DNN Image Restoration Using DNN Hila Levi & Eran Amar Images were taken from: http://people.tuebingen.mpg.de/burger/neural_denoising/ Agenda Domain Expertise vs. End-to-End optimization Image Denoising and

More information

Single Image Super Resolution - When Model Adaptation Matters

Single Image Super Resolution - When Model Adaptation Matters JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2015 1 Single Image Super Resolution - When Model Adaptation Matters arxiv:1703.10889v1 [cs.cv] 31 Mar 2017 Yudong Liang, Radu Timofte, Member, IEEE,

More information

arxiv: v2 [cs.cv] 4 Nov 2018

arxiv: v2 [cs.cv] 4 Nov 2018 arxiv:1811.00344v2 [cs.cv] 4 Nov 2018 Analyzing Perception-Distortion Tradeoff using Enhanced Perceptual Super-resolution Network Subeesh Vasu 1, Nimisha Thekke Madam 2, and Rajagopalan A.N. 3 Indian Institute

More information

Face Recognition A Deep Learning Approach

Face Recognition A Deep Learning Approach Face Recognition A Deep Learning Approach Lihi Shiloh Tal Perl Deep Learning Seminar 2 Outline What about Cat recognition? Classical face recognition Modern face recognition DeepFace FaceNet Comparison

More information

Super-Resolution on Image and Video

Super-Resolution on Image and Video Super-Resolution on Image and Video Jason Liu Stanford University liujas00@stanford.edu Max Spero Stanford University maxspero@stanford.edu Allan Raventos Stanford University aravento@stanford.edu Abstract

More information

CENG 783. Special topics in. Deep Learning. AlchemyAPI. Week 11. Sinan Kalkan

CENG 783. Special topics in. Deep Learning. AlchemyAPI. Week 11. Sinan Kalkan CENG 783 Special topics in Deep Learning AlchemyAPI Week 11 Sinan Kalkan TRAINING A CNN Fig: http://www.robots.ox.ac.uk/~vgg/practicals/cnn/ Feed-forward pass Note that this is written in terms of the

More information

Fully Convolutional Networks for Semantic Segmentation

Fully Convolutional Networks for Semantic Segmentation Fully Convolutional Networks for Semantic Segmentation Jonathan Long* Evan Shelhamer* Trevor Darrell UC Berkeley Chaim Ginzburg for Deep Learning seminar 1 Semantic Segmentation Define a pixel-wise labeling

More information