Computing the Stereo Matching Cost with CNN
|
|
- Christiana Byrd
- 6 years ago
- Views:
Transcription
1 University at Austin Figure. The of lefttexas column displays the left input image, while the right column displays the output of our stereo method. Examples are sorted by difficulty, with easy examples appearing at the top. Some of the difficulties include reflective surfaces, occlusions, as well as regions with many jumps in disparity, e.g. fences and shrubbery. The examples towards the bottom were selected to highlight the flaws in our method and to demonstrate the inherent difficulties of stereo matching on real-world images. Computing the Stereo Matching Cost with CNN differences. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 31(): Tongliang Liao Guillaume Dardelet learning multiple experts behaviors. In BMVC, pages
2 Introduction Traditional Vision paper for stereo matching Plus CNN as a component followed by post-processing pipelines Not an end-to-end solution
3 Stereo Matching 2 cameras: left/right Match pixels Compute pixel-wise disparity Left input image Only horizontal Disparity -> Depth info Right input image Figure 1. The input is a pair of images from the left and right ca
4 Left input image Output disparity map Right input image 0 m 20 m 1.7 m gure 1. The input is a pair of images from the left and right camera. The two input images differ mostly in horizontal locations of obj ote that objects closer to the camera have larger disparities than objects farther away. The output is a dense disparity map shown on ght, with warmer colors representing larger values of disparity (and smaller values of depth). 3] constructed a new dataset of 30 stereo pairs and used 3.1. Creating the dataset
5 Stereo Matching Left input image Minimize energy/cost function Similarity Smoothness Right input image Figure 1. The input is a pair of images from the left and right ca
6 Architecture Left image patch Right image patch x input L1: L2: Patch-wise lower part L3: concatenate 400 L4: Cross-patch upper part L: L6: L7: L8: 2
7 Architecture x input Patch-wise lower part Left image patch Right image patch 1 Conv FC L1: No pooling L2: Cross-patch upper part L3: concatenate 400
8 Architecture x input L3: concatenate 400 Patch-wise lower part L4: Cross-patch upper part L: Pixel pair within 1xD window L6: Concat L7: FC Output (softmax) match/mismatch L8: 2
9 Architecture Left image patch Right image patch 1 Conv x input No pooling / padding L1: 7 FC Patch-wise lower part L2: ReLU L3: concatenate 400 Cross-patch upper part L4: Preprocess lower part L: L6: Feed L3 pair to upper part Decision output L7: L8: 2
10 Training x input Left image patch Right image patch Disparity ground truth L1: Patch-wise lower part L2: Relax disparity L3: concatenate 400 Cross-patch upper part mark close answer as L4: correct L: L6: Decision output L7: L8: 2
11 Initial Cost x input Left image patch Right image patch L1: 1 output vector per pixel Patch-wise lower part L2: L3: concatenate Cross-patch upper part L4: L: Decision output L6: L7: L8: 2
12 Segmentation top arm q horizontal arms of q [±d, ±d] window Similar color left arm p l p right arm bottom arm re 3. The support region for position p, is the union of
13 Segmentation [±d, ±d] window top arm Similar color q horizontal arms of q For each pixel pair take intersection left arm p l p right arm average cost Repeat 4 times. for blurry boundary bottom arm re 3. The support region for position p, is the union of
14 Minimization top arm q horizontal arms of q Minimize energy I: input image D: disparity left arm p l p right arm Cost + f( I, D) bottom arm re 3. The support region for position p, is the union of
15 Minimization Minimize energy top arm I: input image D: disparity q horizontal arms of q Cost + f( I, D) left arm p l p right arm DP along x/y average results only semi-optimal bottom arm re 3. The support region for position p, is the union of
16 Consistency Remove inconsistent regions linear interpolate top arm Smooth the disparity quadratic interpolate q horizontal arms of q left arm p l p right arm Fill boundary copy boundary pixels blur median + gaussian within shape bottom arm re 3. The support region for position p, is the union of
17 Result 14 grayscale images 4M patches Training: h Prediction: 0.01 fps (% time on CNN) 2.61% error
18 Pros
19 Accuracy rforming stereo algorithms on this dataset. Method Error MC-CNN This paper 2.61 % SPS-StFl Yamaguchi et al. [20] 2.83 % Best at that time VC-SF Vogel et al. [16] 3.0 % CoP Anonymous submission 3.30 % SPS-St Yamaguchi et al. [20] 3.3 % PCBP-SS Yamaguchi et al. [1] 3.40 % Current best: PSMNet: 1.61% DDS-SS Anonymous submission 3.83 % StereoSLIC Yamaguchi et al. [1] 3.2 % PR-Sf+E Vogel et al. [17] 4.02 % PCBP Yamaguchi et al. [18] 4.04 % The KITTI stereo leaderboard as it stands in November
20 Performance Profile Component Convolutional neural network Semiglobal matching Cross-based cost aggregation Everything else Runtime s 3 s 2 s 0.03 s PSMNet: 1.61% / 1.3s GC-NET: 1.77% / 0.s
21 CUDA Implementation Component Convolutional neural network Semiglobal matching Cross-based cost aggregation Everything else Runtime s 3 s 2 s 0.03 s CUDA for stereo algorithms
22 Data Size Vary the training set Linear boost Error 3.6 % 3.6 % 3. % 3. % 3.4 % 3.4 % 3.3 % 3.3 % 3.2 % Number of training stereo pairs ure 4. The error on the test set as a function of the number
arxiv: v2 [cs.cv] 20 Oct 2015
Computing the Stereo Matching Cost with a Convolutional Neural Network Jure Žbontar University of Ljubljana jure.zbontar@fri.uni-lj.si Yann LeCun New York University yann@cs.nyu.edu arxiv:1409.4326v2 [cs.cv]
More informationarxiv: v2 [cs.cv] 18 May 2016
Journal of Machine Learning Research 17 (2016) 1-32 Submitted 10/15; Revised 4/16; Published 4/16 Stereo Matching by Training a Convolutional Neural Network to Compare Image Patches arxiv:1510.05970v2
More informationDepth from Stereo. Dominic Cheng February 7, 2018
Depth from Stereo Dominic Cheng February 7, 2018 Agenda 1. Introduction to stereo 2. Efficient Deep Learning for Stereo Matching (W. Luo, A. Schwing, and R. Urtasun. In CVPR 2016.) 3. Cascade Residual
More informationDepth from Stereo. Sanja Fidler CSC420: Intro to Image Understanding 1/ 12
Depth from Stereo Sanja Fidler CSC420: Intro to Image Understanding 1/ 12 Depth from Two Views: Stereo All points on projective line to P map to p Figure: One camera Sanja Fidler CSC420: Intro to Image
More informationUsings CNNs to Estimate Depth from Stereo Imagery
1 Usings CNNs to Estimate Depth from Stereo Imagery Tyler S. Jordan, Skanda Shridhar, Jayant Thatte Abstract This paper explores the benefit of using Convolutional Neural Networks in generating a disparity
More informationVisual Perception for Autonomous Driving on the NVIDIA DrivePX2 and using SYNTHIA
Visual Perception for Autonomous Driving on the NVIDIA DrivePX2 and using SYNTHIA Dr. Juan C. Moure Dr. Antonio Espinosa http://grupsderecerca.uab.cat/hpca4se/en/content/gpu http://adas.cvc.uab.es/elektra/
More informationAdaDepth: 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 informationEfficient Deep Learning for Stereo Matching
Efficient Deep Learning for Stereo Matching Wenjie Luo Alexander G. Schwing Raquel Urtasun Department of Computer Science, University of Toronto {wenjie, aschwing, urtasun}@cs.toronto.edu Abstract In the
More informationPOINT 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 information3D Object Classification via Spherical Projections
3D Object Classification via Spherical Projections Zhangjie Cao 1,QixingHuang 2,andRamaniKarthik 3 1 School of Software Tsinghua University, China 2 Department of Computer Science University of Texas at
More informationConvolution Neural Networks for Chinese Handwriting Recognition
Convolution Neural Networks for Chinese Handwriting Recognition Xu Chen Stanford University 450 Serra Mall, Stanford, CA 94305 xchen91@stanford.edu Abstract Convolutional neural networks have been proven
More informationPredicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture David Eigen, Rob Fergus
Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture David Eigen, Rob Fergus Presented by: Rex Ying and Charles Qi Input: A Single RGB Image Estimate
More informationStereo Matching, Optical Flow, Filling the Gaps and more
Stereo Matching, Optical Flow, Filling the Gaps and more Prof. Lior Wolf The School of Computer Science, Tel-Aviv University ICRI-CI 2017 Retreat, May 9, 2017 Since last year, ICRI-CI supported projects
More informationPresented at the FIG Congress 2018, May 6-11, 2018 in Istanbul, Turkey
Presented at the FIG Congress 2018, May 6-11, 2018 in Istanbul, Turkey Evangelos MALTEZOS, Charalabos IOANNIDIS, Anastasios DOULAMIS and Nikolaos DOULAMIS Laboratory of Photogrammetry, School of Rural
More informationDeep 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 informationFlow Estimation. Min Bai. February 8, University of Toronto. Min Bai (UofT) Flow Estimation February 8, / 47
Flow Estimation Min Bai University of Toronto February 8, 2016 Min Bai (UofT) Flow Estimation February 8, 2016 1 / 47 Outline Optical Flow - Continued Min Bai (UofT) Flow Estimation February 8, 2016 2
More informationLecture 14: Computer Vision
CS/b: Artificial Intelligence II Prof. Olga Veksler Lecture : Computer Vision D shape from Images Stereo Reconstruction Many Slides are from Steve Seitz (UW), S. Narasimhan Outline Cues for D shape perception
More informationCIS680: Vision & Learning Assignment 2.b: RPN, Faster R-CNN and Mask R-CNN Due: Nov. 21, 2018 at 11:59 pm
CIS680: Vision & Learning Assignment 2.b: RPN, Faster R-CNN and Mask R-CNN Due: Nov. 21, 2018 at 11:59 pm Instructions This is an individual assignment. Individual means each student must hand in their
More informationRGBD Occlusion Detection via Deep Convolutional Neural Networks
1 RGBD Occlusion Detection via Deep Convolutional Neural Networks Soumik Sarkar 1,2, Vivek Venugopalan 1, Kishore Reddy 1, Michael Giering 1, Julian Ryde 3, Navdeep Jaitly 4,5 1 United Technologies Research
More informationTraining models for road scene understanding with automated ground truth Dan Levi
Training models for road scene understanding with automated ground truth Dan Levi With: Noa Garnett, Ethan Fetaya, Shai Silberstein, Rafi Cohen, Shaul Oron, Uri Verner, Ariel Ayash, Kobi Horn, Vlad Golder,
More informationDeep Learning-driven Depth from Defocus via Active Multispectral Quasi-random Projections with Complex Subpatterns
Deep Learning-driven Depth from Defocus via Active Multispectral Quasi-random Projections with Complex Subpatterns Avery Ma avery.ma@uwaterloo.ca Alexander Wong a28wong@uwaterloo.ca David A Clausi dclausi@uwaterloo.ca
More informationClassification of objects from Video Data (Group 30)
Classification of objects from Video Data (Group 30) Sheallika Singh 12665 Vibhuti Mahajan 12792 Aahitagni Mukherjee 12001 M Arvind 12385 1 Motivation Video surveillance has been employed for a long time
More informationImplementing Deep Learning for Video Analytics on Tegra X1.
Implementing Deep Learning for Video Analytics on Tegra X1 research@hertasecurity.com Index Who we are, what we do Video analytics pipeline Video decoding Facial detection and preprocessing DNN: learning
More informationEVALUATION OF DEEP LEARNING BASED STEREO MATCHING METHODS: FROM GROUND TO AERIAL IMAGES
EVALUATION OF DEEP LEARNING BASED STEREO MATCHING METHODS: FROM GROUND TO AERIAL IMAGES J. Liu 1, S. Ji 1,*, C. Zhang 1, Z. Qin 1 1 School of Remote Sensing and Information Engineering, Wuhan University,
More informationLecture 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 informationMachine Learning 13. week
Machine Learning 13. week Deep Learning Convolutional Neural Network Recurrent Neural Network 1 Why Deep Learning is so Popular? 1. Increase in the amount of data Thanks to the Internet, huge amount of
More informationDeep Tracking: Biologically Inspired Tracking with Deep Convolutional Networks
Deep Tracking: Biologically Inspired Tracking with Deep Convolutional Networks Si Chen The George Washington University sichen@gwmail.gwu.edu Meera Hahn Emory University mhahn7@emory.edu Mentor: Afshin
More informationPointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space Sikai Zhong February 14, 2018 COMPUTER SCIENCE Table of contents 1. PointNet 2. PointNet++ 3. Experiments 1 PointNet Property
More informationarxiv: v1 [cs.cv] 23 Mar 2018
Pyramid Stereo Matching Network Jia-Ren Chang Yong-Sheng Chen Department of Computer Science, National Chiao Tung University, Taiwan {followwar.cs00g, yschen}@nctu.edu.tw arxiv:03.0669v [cs.cv] 3 Mar 0
More informationStereo: Disparity and Matching
CS 4495 Computer Vision Aaron Bobick School of Interactive Computing Administrivia PS2 is out. But I was late. So we pushed the due date to Wed Sept 24 th, 11:55pm. There is still *no* grace period. To
More informationCAP 6412 Advanced Computer Vision
CAP 6412 Advanced Computer Vision http://www.cs.ucf.edu/~bgong/cap6412.html Boqing Gong April 21st, 2016 Today Administrivia Free parameters in an approach, model, or algorithm? Egocentric videos by Aisha
More informationSingle 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 informationCS231N Section. Video Understanding 6/1/2018
CS231N Section Video Understanding 6/1/2018 Outline Background / Motivation / History Video Datasets Models Pre-deep learning CNN + RNN 3D convolution Two-stream What we ve seen in class so far... Image
More informationDeep 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 informationCNN for Low Level Image Processing. Huanjing Yue
CNN for Low Level Image Processing Huanjing Yue 2017.11 1 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
More informationDeep Models for 3D Reconstruction
Deep Models for 3D Reconstruction Andreas Geiger Autonomous Vision Group, MPI for Intelligent Systems, Tübingen Computer Vision and Geometry Group, ETH Zürich October 12, 2017 Max Planck Institute for
More informationSPNet: Shape Prediction using a Fully Convolutional Neural Network
SPNet: Shape Prediction using a Fully Convolutional Neural Network S M Masudur Rahman Al Arif 1, Karen Knapp 2 and Greg Slabaugh 1 1 City, University of London 2 University of Exeter Abstract. Shape has
More informationMulti-Task Self-Supervised Visual Learning
Multi-Task Self-Supervised Visual Learning Sikai Zhong March 4, 2018 COMPUTER SCIENCE Table of contents 1. Introduction 2. Self-supervised Tasks 3. Architectures 4. Experiments 1 Introduction Self-supervised
More informationCHAPTER 3 DISPARITY AND DEPTH MAP COMPUTATION
CHAPTER 3 DISPARITY AND DEPTH MAP COMPUTATION In this chapter we will discuss the process of disparity computation. It plays an important role in our caricature system because all 3D coordinates of nodes
More informationDeep Learning with Tensorflow AlexNet
Machine Learning and Computer Vision Group Deep Learning with Tensorflow http://cvml.ist.ac.at/courses/dlwt_w17/ AlexNet Krizhevsky, Alex, Ilya Sutskever, and Geoffrey E. Hinton, "Imagenet classification
More information3D Shape Analysis with Multi-view Convolutional Networks. Evangelos Kalogerakis
3D Shape Analysis with Multi-view Convolutional Networks Evangelos Kalogerakis 3D model repositories [3D Warehouse - video] 3D geometry acquisition [KinectFusion - video] 3D shapes come in various flavors
More informationObject Localization, Segmentation, Classification, and Pose Estimation in 3D Images using Deep Learning
Allan Zelener Dissertation Proposal December 12 th 2016 Object Localization, Segmentation, Classification, and Pose Estimation in 3D Images using Deep Learning Overview 1. Introduction to 3D Object Identification
More informationCOS Lecture 10 Autonomous Robot Navigation
COS 495 - Lecture 10 Autonomous Robot Navigation Instructor: Chris Clark Semester: Fall 2011 1 Figures courtesy of Siegwart & Nourbakhsh Control Structure Prior Knowledge Operator Commands Localization
More informationSSD: 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 informationSemantic Segmentation
Semantic Segmentation UCLA:https://goo.gl/images/I0VTi2 OUTLINE Semantic Segmentation Why? Paper to talk about: Fully Convolutional Networks for Semantic Segmentation. J. Long, E. Shelhamer, and T. Darrell,
More informationDeep Learning on Graphs
Deep Learning on Graphs with Graph Convolutional Networks Hidden layer Hidden layer Input Output ReLU ReLU, 6 April 2017 joint work with Max Welling (University of Amsterdam) The success story of deep
More informationDeep Learning in Image Processing
Deep Learning in Image Processing Roland Memisevic University of Montreal & TwentyBN ICISP 2016 Roland Memisevic Deep Learning in Image Processing ICISP 2016 f 2? cathedral high-rise f 1 It s the features,
More informationNVIDIA FOR DEEP LEARNING. Bill Veenhuis
NVIDIA FOR DEEP LEARNING Bill Veenhuis bveenhuis@nvidia.com Nvidia is the world s leading ai platform ONE ARCHITECTURE CUDA 2 GPU: Perfect Companion for Accelerating Apps & A.I. CPU GPU 3 Intro to AI AGENDA
More informationDeepLab: 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 informationLight 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 informationR-FCN: Object Detection with Really - Friggin Convolutional Networks
R-FCN: Object Detection with Really - Friggin Convolutional Networks Jifeng Dai Microsoft Research Li Yi Tsinghua Univ. Kaiming He FAIR Jian Sun Microsoft Research NIPS, 2016 Or Region-based Fully Convolutional
More informationEmbedded real-time stereo estimation via Semi-Global Matching on the GPU
Embedded real-time stereo estimation via Semi-Global Matching on the GPU Daniel Hernández Juárez, Alejandro Chacón, Antonio Espinosa, David Vázquez, Juan Carlos Moure and Antonio M. López Computer Architecture
More informationarxiv: v1 [cs.cv] 31 Mar 2016
Object Boundary Guided Semantic Segmentation Qin Huang, Chunyang Xia, Wenchao Zheng, Yuhang Song, Hao Xu and C.-C. Jay Kuo arxiv:1603.09742v1 [cs.cv] 31 Mar 2016 University of Southern California Abstract.
More informationarxiv: v1 [cs.cv] 21 Sep 2018
arxiv:1809.07977v1 [cs.cv] 21 Sep 2018 Real-Time Stereo Vision on FPGAs with SceneScan Konstantin Schauwecker 1 Nerian Vision GmbH, Gutenbergstr. 77a, 70197 Stuttgart, Germany www.nerian.com Abstract We
More informationSupplementary Material for Sparsity Invariant CNNs
Supplementary Material for Sparsity Invariant CNNs Jonas Uhrig,1,2 Nick Schneider,1,3 Lukas Schneider 1,4 Uwe Franke 1 Thomas Brox 2 Andreas Geiger 4,5 1 Daimler R&D Sindelfingen 2 University of Freiburg
More informationSupplementary: Cross-modal Deep Variational Hand Pose Estimation
Supplementary: Cross-modal Deep Variational Hand Pose Estimation Adrian Spurr, Jie Song, Seonwook Park, Otmar Hilliges ETH Zurich {spurra,jsong,spark,otmarh}@inf.ethz.ch Encoder/Decoder Linear(512) Table
More informationSupplementary Material for Zoom and Learn: Generalizing Deep Stereo Matching to Novel Domains
Supplementary Material for Zoom and Learn: Generalizing Deep Stereo Matching to Novel Domains Jiahao Pang 1 Wenxiu Sun 1 Chengxi Yang 1 Jimmy Ren 1 Ruichao Xiao 1 Jin Zeng 1 Liang Lin 1,2 1 SenseTime Research
More informationLearning visual odometry with a convolutional network
Learning visual odometry with a convolutional network Kishore Konda 1, Roland Memisevic 2 1 Goethe University Frankfurt 2 University of Montreal konda.kishorereddy@gmail.com, roland.memisevic@gmail.com
More informationDeep Learning on Graphs
Deep Learning on Graphs with Graph Convolutional Networks Hidden layer Hidden layer Input Output ReLU ReLU, 22 March 2017 joint work with Max Welling (University of Amsterdam) BDL Workshop @ NIPS 2016
More information3 Object Detection. BVM 2018 Tutorial: Advanced Deep Learning Methods. Paul F. Jaeger, Division of Medical Image Computing
3 Object Detection BVM 2018 Tutorial: Advanced Deep Learning Methods Paul F. Jaeger, of Medical Image Computing What is object detection? classification segmentation obj. detection (1 label per pixel)
More informationRegionlet Object Detector with Hand-crafted and CNN Feature
Regionlet Object Detector with Hand-crafted and CNN Feature Xiaoyu Wang Research Xiaoyu Wang Research Ming Yang Horizon Robotics Shenghuo Zhu Alibaba Group Yuanqing Lin Baidu Overview of this section Regionlet
More informationRecurrent Convolutional Neural Networks for Scene Labeling
Recurrent Convolutional Neural Networks for Scene Labeling Pedro O. Pinheiro, Ronan Collobert Reviewed by Yizhe Zhang August 14, 2015 Scene labeling task Scene labeling: assign a class label to each pixel
More informationOptical flow. Cordelia Schmid
Optical flow Cordelia Schmid Motion field The motion field is the projection of the 3D scene motion into the image Optical flow Definition: optical flow is the apparent motion of brightness patterns in
More informationS7348: Deep Learning in Ford's Autonomous Vehicles. Bryan Goodman Argo AI 9 May 2017
S7348: Deep Learning in Ford's Autonomous Vehicles Bryan Goodman Argo AI 9 May 2017 1 Ford s 12 Year History in Autonomous Driving Today: examples from Stereo image processing Object detection Using RNN
More informationLecture 10 Multi-view Stereo (3D Dense Reconstruction) Davide Scaramuzza
Lecture 10 Multi-view Stereo (3D Dense Reconstruction) Davide Scaramuzza REMODE: Probabilistic, Monocular Dense Reconstruction in Real Time, ICRA 14, by Pizzoli, Forster, Scaramuzza [M. Pizzoli, C. Forster,
More informationIntroduction to Neural Networks
Introduction to Neural Networks Jakob Verbeek 2017-2018 Biological motivation Neuron is basic computational unit of the brain about 10^11 neurons in human brain Simplified neuron model as linear threshold
More informationGenerative 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 informationData Term. Michael Bleyer LVA Stereo Vision
Data Term Michael Bleyer LVA Stereo Vision What happened last time? We have looked at our energy function: E ( D) = m( p, dp) + p I < p, q > N s( p, q) We have learned about an optimization algorithm that
More informationDeep Learning For Video Classification. Presented by Natalie Carlebach & Gil Sharon
Deep Learning For Video Classification Presented by Natalie Carlebach & Gil Sharon Overview Of Presentation Motivation Challenges of video classification Common datasets 4 different methods presented in
More informationDEEP BLIND IMAGE QUALITY ASSESSMENT
DEEP BLIND IMAGE QUALITY ASSESSMENT BY LEARNING SENSITIVITY MAP Jongyoo Kim, Woojae Kim and Sanghoon Lee ICASSP 2018 Deep Learning and Convolutional Neural Networks (CNNs) SOTA in computer vision & image
More informationDeep Learning. Deep Learning provided breakthrough results in speech recognition and image classification. Why?
Data Mining Deep Learning Deep Learning provided breakthrough results in speech recognition and image classification. Why? Because Speech recognition and image classification are two basic examples of
More informationVideo Object Segmentation using Deep Learning
Video Object Segmentation using Deep Learning Zack While Youngstown State University zackwhile@outlook.com Chen Chen chenchen870713@gmail.com Mubarak Shah shah@crcv.ucf.edu Rui Hou houray@gmail.com Abstract
More informationDeep Face Recognition. Nathan Sun
Deep Face Recognition Nathan Sun Why Facial Recognition? Picture ID or video tracking Higher Security for Facial Recognition Software Immensely useful to police in tracking suspects Your face will be an
More informationDeep Learning for Computer Vision with MATLAB By Jon Cherrie
Deep Learning for Computer Vision with MATLAB By Jon Cherrie 2015 The MathWorks, Inc. 1 Deep learning is getting a lot of attention "Dahl and his colleagues won $22,000 with a deeplearning system. 'We
More informationDeep Incremental Scene Understanding. Federico Tombari & Christian Rupprecht Technical University of Munich, Germany
Deep Incremental Scene Understanding Federico Tombari & Christian Rupprecht Technical University of Munich, Germany C. Couprie et al. "Toward Real-time Indoor Semantic Segmentation Using Depth Information"
More informationConditional Random Fields as Recurrent Neural Networks
BIL722 - Deep Learning for Computer Vision Conditional Random Fields as Recurrent Neural Networks S. Zheng, S. Jayasumana, B. Romera-Paredes V. Vineet, Z. Su, D. Du, C. Huang, P.H.S. Torr Introduction
More informationSemantic Segmentation. Zhongang Qi
Semantic Segmentation Zhongang Qi qiz@oregonstate.edu Semantic Segmentation "Two men riding on a bike in front of a building on the road. And there is a car." Idea: recognizing, understanding what's in
More informationarxiv: 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 informationKnow your data - many types of networks
Architectures Know your data - many types of networks Fixed length representation Variable length representation Online video sequences, or samples of different sizes Images Specific architectures for
More informationFlow-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 informationCascade Residual Learning: A Two-stage Convolutional Neural Network for Stereo Matching
Cascade Residual Learning: A Two-stage Convolutional Neural Network for Stereo Matching Jiahao Pang Wenxiu Sun Jimmy SJ. Ren Chengxi Yang Qiong Yan SenseTime Group Limited {pangjiahao, sunwenxiu, rensijie,
More informationInstance-aware Semantic Segmentation via Multi-task Network Cascades
Instance-aware Semantic Segmentation via Multi-task Network Cascades Jifeng Dai, Kaiming He, Jian Sun Microsoft research 2016 Yotam Gil Amit Nativ Agenda Introduction Highlights Implementation Further
More informationJoint Object Detection and Viewpoint Estimation using CNN features
Joint Object Detection and Viewpoint Estimation using CNN features Carlos Guindel, David Martín and José M. Armingol cguindel@ing.uc3m.es Intelligent Systems Laboratory Universidad Carlos III de Madrid
More informationComputer Vision I. Dense Stereo Correspondences. Anita Sellent 1/15/16
Computer Vision I Dense Stereo Correspondences Anita Sellent Stereo Two Cameras Overlapping field of view Known transformation between cameras From disparity compute depth [ Bradski, Kaehler: Learning
More informationObject Detection. CS698N Final Project Presentation AKSHAT AGARWAL SIDDHARTH TANWAR
Object Detection CS698N Final Project Presentation AKSHAT AGARWAL SIDDHARTH TANWAR Problem Description Arguably the most important part of perception Long term goals for object recognition: Generalization
More informationBinocular stereo. Given a calibrated binocular stereo pair, fuse it to produce a depth image. Where does the depth information come from?
Binocular Stereo Binocular stereo Given a calibrated binocular stereo pair, fuse it to produce a depth image Where does the depth information come from? Binocular stereo Given a calibrated binocular stereo
More information3D Convolutional Neural Networks for Landing Zone Detection from LiDAR
3D Convolutional Neural Networks for Landing Zone Detection from LiDAR Daniel Mataruna and Sebastian Scherer Presented by: Sabin Kafle Outline Introduction Preliminaries Approach Volumetric Density Mapping
More informationSegmentation Based Stereo. Michael Bleyer LVA Stereo Vision
Segmentation Based Stereo Michael Bleyer LVA Stereo Vision What happened last time? Once again, we have looked at our energy function: E ( D) = m( p, dp) + p I < p, q > We have investigated the matching
More informationBeyond local reasoning for stereo confidence estimation with deep learning
Beyond local reasoning for stereo confidence estimation with deep learning Fabio Tosi, Matteo Poggi, Antonio Benincasa, and Stefano Mattoccia University of Bologna, Viale del Risorgimento 2, Bologna, Italy
More informationMulti-View 3D Object Detection Network for Autonomous Driving
Multi-View 3D Object Detection Network for Autonomous Driving Xiaozhi Chen, Huimin Ma, Ji Wan, Bo Li, Tian Xia CVPR 2017 (Spotlight) Presented By: Jason Ku Overview Motivation Dataset Network Architecture
More informationLecture 6 Stereo Systems Multi-view geometry
Lecture 6 Stereo Systems Multi-view geometry Professor Silvio Savarese Computational Vision and Geometry Lab Silvio Savarese Lecture 6-5-Feb-4 Lecture 6 Stereo Systems Multi-view geometry Stereo systems
More informationIntro to Deep Learning. Slides Credit: Andrej Karapathy, Derek Hoiem, Marc Aurelio, Yann LeCunn
Intro to Deep Learning Slides Credit: Andrej Karapathy, Derek Hoiem, Marc Aurelio, Yann LeCunn Why this class? Deep Features Have been able to harness the big data in the most efficient and effective
More informationDepth Learning: When Depth Estimation Meets Deep Learning
Depth Learning: When Depth Estimation Meets Deep Learning Prof. Liang LIN SenseTime Research & Sun Yat-sen University NITRE, June 18, 2018 Outline Part 1. Introduction Motivation Stereo Matching Single
More informationDeep Learning. Visualizing and Understanding Convolutional Networks. Christopher Funk. Pennsylvania State University.
Visualizing and Understanding Convolutional Networks Christopher Pennsylvania State University February 23, 2015 Some Slide Information taken from Pierre Sermanet (Google) presentation on and Computer
More informationarxiv: v1 [cs.cv] 16 Nov 2018
Improving Rotated Text Detection with Rotation Region Proposal Networks Jing Huang 1, Viswanath Sivakumar 1, Mher Mnatsakanyan 1,2 and Guan Pang 1 1 Facebook Inc. 2 University of California, Berkeley November
More informationCONVOLUTIONAL COST AGGREGATION FOR ROBUST STEREO MATCHING. Somi Jeong Seungryong Kim Bumsub Ham Kwanghoon Sohn
CONVOLUTIONAL COST AGGREGATION FOR ROBUST STEREO MATCHING Somi Jeong Seungryong Kim Bumsub Ham Kwanghoon Sohn School of Electrical and Electronic Engineering, Yonsei University, Seoul, Korea E-mail: khsohn@yonsei.ac.kr
More informationMRI Tumor Segmentation with Densely Connected 3D CNN. Lele Chen, Yue Wu, Adora M. DSouze, Anas Z. Abidin, Axel Wismüller, and Chenliang Xu
1 MRI Tumor Segmentation with Densely Connected 3D CNN Lele Chen, Yue Wu, Adora M. DSouze, Anas Z. Abidin, Axel Wismüller, and MRI Brain Tumor Segmentation 2 Image source: https://github.com/naldeborgh7575/brain_segmentation
More informationUNSUPERVISED STEREO MATCHING USING CORRESPONDENCE CONSISTENCY. Sunghun Joung Seungryong Kim Bumsub Ham Kwanghoon Sohn
UNSUPERVISED STEREO MATCHING USING CORRESPONDENCE CONSISTENCY Sunghun Joung Seungryong Kim Bumsub Ham Kwanghoon Sohn School of Electrical and Electronic Engineering, Yonsei University, Seoul, Korea E-mail:
More informationTEXT SEGMENTATION ON PHOTOREALISTIC IMAGES
TEXT SEGMENTATION ON PHOTOREALISTIC IMAGES Valery Grishkin a, Alexander Ebral b, Nikolai Stepenko c, Jean Sene d Saint Petersburg State University, 7 9 Universitetskaya nab., Saint Petersburg, 199034,
More informationActiveStereoNet: End-to-End Self-Supervised Learning for Active Stereo Systems (Supplementary Materials)
ActiveStereoNet: End-to-End Self-Supervised Learning for Active Stereo Systems (Supplementary Materials) Yinda Zhang 1,2, Sameh Khamis 1, Christoph Rhemann 1, Julien Valentin 1, Adarsh Kowdle 1, Vladimir
More information