LEARNING RIGIDITY IN DYNAMIC SCENES FOR SCENE FLOW ESTIMATION
|
|
- Maud Ward
- 5 years ago
- Views:
Transcription
1 LEARNING RIGIDITY IN DYNAMIC SCENES FOR SCENE FLOW ESTIMATION Kihwan Kim, Senior Research Scientist Zhaoyang Lv, Kihwan Kim, Alejandro Troccoli, Deqing Sun, James M. Rehg, Jan Kautz
2 CORRESPENDECES IN COMPUTER VISION Image courtesy Roy Shilkrot 2
3 OPTICAL FLOW Fan et al Brox and Malik 2011 Castro M
4 OPTICAL FLOW AND 3D SCENE FLOW Fan et al Brox and Malik 2011 Castro M Letouzey et al
5 APPLICATION OF 3D MOTION 3D reconstruction of dynamic scene AR and telepresence [DynamicFusion, R. Newcombe, CVPR 2016] [Holoportation, Microsoft 2016] 5
6 APPLICATION OF 3D MOTION 3D Scene Understanding for autonomous driving Robotics Interaction [KITTI Dataset, A. Geiger, PAMI 2014] [SE3-Net,A. Byravan, ICRA, 2017] 6
7 2D OPTICAL FLOW VS 3D SCENE FLOW Why 3D motion estimation is challenging? 7
8 STATIC SCENE - MOVING CAMERA Ω 0 x 0 u 0 u 0 u 0 I 0 u 0 I 1 8
9 STATIC SCENE - MOVING CAMERA cm δu 0 1 Optical flow from camera motion Ω 0 x 0 I 0 u 0 u 0 sf0 δu 0 1 cm δu 0 1 u 0 u 0 I 1 9
10 STATIC SCENE - MOVING CAMERA cm δu 0 1 Optical flow from camera motion x 0 Ω 0 Structure (3D) from (camera) Motion I 0 u 0 u 0 sf0 δu 0 1 cm δu 0 1 u 0 u 0 I 1 10
11 DYNAMIC SCENE - FIXED CAMERA Ω 0 x 0 u 0 I 0 11
12 DYNAMIC SCENE - FIXED CAMERA Ω 0 Ω 1 δx 0 1 sf1 δu 0 1 Scene flow Projected scene flow in I 1 x x 1 0 δx 0 1 u 0 sf0 δu0 1 u 1 I 0 12
13 DYNAMIC SCENE - FIXED CAMERA Ω 0 Ω 1 δx 0 1 Scene flow x x 1 0 δx 0 1 u 0 u 1 I 0 13
14 14 COMMON VIDEOS NOWADAYS Giphy.com #gopro, #drone, Sondra.T. 14
15 DYNAMIC SCENE MOVING CAMERA Ω 0 x 0 u 0 I 0 15
16 DYNAMIC SCENE MOVING CAMERA Ω 0 Ω 1 x x 1 0 δx 0 1 u 0 I 0 u 1 u 0 u 1 I 1 16
17 DYNAMIC SCENE MOVING CAMERA sf1 δu 0 1 of δu 0 1 cm δu 0 1 Projected scene flow in I 1 Optical flow Optical flow from camera motion Ω 0 x x 1 0 δx 0 1 Ω 1 I 0 u 0 sf0 δu 0 1 u 1 cm δu 0 1 u 0 u 0 of δu 0 1 sf1 δu 0 1 u 1 I 1 17
18 DYNAMIC SCENE MOVING CAMERA Projected scene flow (3D motion field) Camera Ego motion Input sequence Optical flow Optical flow Camera Pose (transform) Camera ego-motion flow (projected) scene flow or 3D motion field RIGIDITY 18
19 HOW OTHER WORKS SOLVE THIS? Non-rigid or rigid local motions as outliers Yang et al. ICRA 2011 Menze and Geiger. CVPR
20 HOW OTHER FLOW ALGORITHMS SOLVE THIS? Vogel et al. ICCV 2013 Quiroga et al. ECCV 2014 Jaimez et al. 3DV 2015 Jaimez et al. ICRA 2017 Wulff et al. CVPR
21 OUR PROPOSAL Learn which parts of the scene is (likely) rigid/non-rigid 21
22 PIPELINE D 1 I 1 Rigidity Transform Network (RTN) Rigidity Mask [R t] Refinement Refined [R t] Warping D 0 I 0 Flow network PWC-net Optical flow Ego-motion flow Estimated Projected Scene Flow Subtraction In 3D 22
23 RIGIDITY TRANSFORM NETWORK (RTN) D 0 I 0 Deconv 1-5 Rigidity Attention Mask conv1-6 Pose Regressor R t D 1 I 1 23
24 RIGIDITY TRANSFORM NETWORK (RTN) D 0 I 0 Binary cross entropy loss Deconv 1-5 Rigidity Attention Mask D 1 I 1 c o n v 1 c o n v 2 c o n v 3 c o n v 4 c o n v 5 c o n v 6 Global Average Pooling conv-t conv-r R t Huber loss Translation Rotation 24
25 2D OPTICAL FLOW PWCNET CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume Sun et al. CVPR
26 POSE REFINEMENT AND FLOW R t = arg min u,v Ω B u, v = 1 O u, v = 0 L RV 0 u + δu, v + δv + t V 1 u, v Rigidity mask Occlusion mask Flow correspondences We solve this objective function using off-the-shelf Gauss Newton solver GTSAM. 26
27 SUPERVISION NEEDED Scene-net RGB-D SLAM benchmark SINTEL FlyingThings 3D Monkaa RGB-D dataset Lay-out Number Total Images Scenes Pose (GT) Optical flow (GT) Segmentation (GT) Photo realistic Depth realistic Scene-net M static Yes Yes (from pose) Yes No Yes RGB-D SLAM K static Yes No No Yes Yes SINTEL dynamic Yes Yes Yes No Yes FlyingThings - 25K dynamic Yes Yes Yes No No Monkaa - 10K dynamic Yes Yes Yes No Yes 27
28 SEMI-SYNTHETIC DYNAMIC SCENE DATASET 28
29 REFRESH DATASET 29
30 30
31 31
32 SINTEL EVALUATION Trained from our data, testing on SINTEL data 32
33 SINTEL EVALUATION (POSE) 33
34 REAL WORLD DATA EVALUATION 34
35 35
36 CONCLUSION Proposed a learning-based approach to estimate the rigid regions in dynamic scenes observed by a moving camera Robust per-pixel Rigidity of dynamic scenes Camera pose refined jointly together with 2D optical flow and rigid/occlusion masks Novel semi-synthetic dynamic scene dataset, REFRESH Ours outperforms the state-of-the-art in SINTEL Future works End-to-end framework that learns rigidity as well as correspondences More rich contents in dynamic scene data for encouraging more generalization 36
Multiframe Scene Flow with Piecewise Rigid Motion. Vladislav Golyanik,, Kihwan Kim, Robert Maier, Mathias Nießner, Didier Stricker and Jan Kautz
Multiframe Scene Flow with Piecewise Rigid Motion Vladislav Golyanik,, Kihwan Kim, Robert Maier, Mathias Nießner, Didier Stricker and Jan Kautz Scene Flow. 2 Scene Flow. 3 Scene Flow. Scene Flow Estimation:
More informationLearning Rigidity in Dynamic Scenes with a Moving Camera for 3D Motion Field Estimation
Learning Rigidity in Dynamic Scenes with a Moving Camera for 3D Motion Field Estimation Zhaoyang Lv 1, Kihwan Kim 2, Alejandro Troccoli 2, Deqing Sun 2, James M. Rehg 1, Jan Kautz 2 1 Georgia Institute
More informationJakob Engel, Thomas Schöps, Daniel Cremers Technical University Munich. LSD-SLAM: Large-Scale Direct Monocular SLAM
Computer Vision Group Technical University of Munich Jakob Engel LSD-SLAM: Large-Scale Direct Monocular SLAM Jakob Engel, Thomas Schöps, Daniel Cremers Technical University Munich Monocular Video Engel,
More informationCombining Stereo Disparity and Optical Flow for Basic Scene Flow
Combining Stereo Disparity and Optical Flow for Basic Scene Flow René Schuster, Christian Bailer, Oliver Wasenmüller, Didier Stricker DFKI German Research Center for Artificial Intelligence firstname.lastname@dfki.de
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 informationSemi-Dense Direct SLAM
Computer Vision Group Technical University of Munich Jakob Engel Jakob Engel, Daniel Cremers David Caruso, Thomas Schöps, Lukas von Stumberg, Vladyslav Usenko, Jörg Stückler, Jürgen Sturm Technical University
More informationHuman Pose Estimation with Deep Learning. Wei Yang
Human Pose Estimation with Deep Learning Wei Yang Applications Understand Activities Family Robots American Heist (2014) - The Bank Robbery Scene 2 What do we need to know to recognize a crime scene? 3
More informationJoint Unsupervised Learning of Optical Flow and Depth by Watching Stereo Videos
Joint Unsupervised Learning of Optical Flow and Depth by Watching Stereo Videos Yang Wang 1 Zhenheng Yang 2 Peng Wang 1 Yi Yang 1 Chenxu Luo 3 Wei Xu 1 1 Baidu Research 2 University of Southern California
More informationMOTION ESTIMATION USING CONVOLUTIONAL NEURAL NETWORKS. Mustafa Ozan Tezcan
MOTION ESTIMATION USING CONVOLUTIONAL NEURAL NETWORKS Mustafa Ozan Tezcan Boston University Department of Electrical and Computer Engineering 8 Saint Mary s Street Boston, MA 2215 www.bu.edu/ece Dec. 19,
More information3D Object Recognition and Scene Understanding from RGB-D Videos. Yu Xiang Postdoctoral Researcher University of Washington
3D Object Recognition and Scene Understanding from RGB-D Videos Yu Xiang Postdoctoral Researcher University of Washington 1 2 Act in the 3D World Sensing & Understanding Acting Intelligent System 3D World
More informationDense Tracking and Mapping for Autonomous Quadrocopters. Jürgen Sturm
Computer Vision Group Prof. Daniel Cremers Dense Tracking and Mapping for Autonomous Quadrocopters Jürgen Sturm Joint work with Frank Steinbrücker, Jakob Engel, Christian Kerl, Erik Bylow, and Daniel Cremers
More informationFast 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 informationPerceiving the 3D World from Images and Videos. Yu Xiang Postdoctoral Researcher University of Washington
Perceiving the 3D World from Images and Videos Yu Xiang Postdoctoral Researcher University of Washington 1 2 Act in the 3D World Sensing & Understanding Acting Intelligent System 3D World 3 Understand
More informationJOINT 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 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 informationIntrinsic3D: High-Quality 3D Reconstruction by Joint Appearance and Geometry Optimization with Spatially-Varying Lighting
Intrinsic3D: High-Quality 3D Reconstruction by Joint Appearance and Geometry Optimization with Spatially-Varying Lighting R. Maier 1,2, K. Kim 1, D. Cremers 2, J. Kautz 1, M. Nießner 2,3 Fusion Ours 1
More informationHybrids Mixed Approaches
Hybrids Mixed Approaches Stephan Weiss Computer Vision Group NASA-JPL / CalTech Stephan.Weiss@ieee.org (c) 2013. Government sponsorship acknowledged. Outline Why mixing? Parallel Tracking and Mapping Benefits
More informationDense 3D Reconstruction from Autonomous Quadrocopters
Dense 3D Reconstruction from Autonomous Quadrocopters Computer Science & Mathematics TU Munich Martin Oswald, Jakob Engel, Christian Kerl, Frank Steinbrücker, Jan Stühmer & Jürgen Sturm Autonomous Quadrocopters
More informationSupplementary Material The Best of Both Worlds: Combining CNNs and Geometric Constraints for Hierarchical Motion Segmentation
Supplementary Material The Best of Both Worlds: Combining CNNs and Geometric Constraints for Hierarchical Motion Segmentation Pia Bideau Aruni RoyChowdhury Rakesh R Menon Erik Learned-Miller University
More informationReconstruction, Motion Estimation and SLAM from Events
Reconstruction, Motion Estimation and SLAM from Events Andrew Davison Robot Vision Group and Dyson Robotics Laboratory Department of Computing Imperial College London www.google.com/+andrewdavison June
More informationDeep 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 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 informationOpenStreetSLAM: Global Vehicle Localization using OpenStreetMaps
OpenStreetSLAM: Global Vehicle Localization using OpenStreetMaps Georgios Floros, Benito van der Zander and Bastian Leibe RWTH Aachen University, Germany http://www.vision.rwth-aachen.de floros@vision.rwth-aachen.de
More informationA Fusion Approach for Multi-Frame Optical Flow Estimation
A Fusion Approach for Multi-Frame Optical Estimation Zhile Ren Orazio Gallo Deqing Sun Ming-Hsuan Yang Erik B. Sudderth Jan Kautz Georgia Tech NVIDIA UC Merced UC Irvine NVIDIA Abstract To date, top-performing
More informationarxiv: v1 [cs.cv] 25 Feb 2019
DD: Learning Optical with Unlabeled Data Distillation Pengpeng Liu, Irwin King, Michael R. Lyu, Jia Xu The Chinese University of Hong Kong, Shatin, N.T., Hong Kong Tencent AI Lab, Shenzhen, China {ppliu,
More informationEasyChair Preprint. Visual Odometry Based on Convolutional Neural Networks for Large-Scale Scenes
EasyChair Preprint 413 Visual Odometry Based on Convolutional Neural Networks for Large-Scale Scenes Xuyang Meng, Chunxiao Fan and Yue Ming EasyChair preprints are intended for rapid dissemination of research
More informationMultilayer 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 informationDense 3D Modelling and Monocular Reconstruction of Deformable Objects
Dense 3D Modelling and Monocular Reconstruction of Deformable Objects Anastasios (Tassos) Roussos Lecturer in Computer Science, University of Exeter Research Associate, Imperial College London Overview
More informationDirect Methods in Visual Odometry
Direct Methods in Visual Odometry July 24, 2017 Direct Methods in Visual Odometry July 24, 2017 1 / 47 Motivation for using Visual Odometry Wheel odometry is affected by wheel slip More accurate compared
More informationColored Point Cloud Registration Revisited Supplementary Material
Colored Point Cloud Registration Revisited Supplementary Material Jaesik Park Qian-Yi Zhou Vladlen Koltun Intel Labs A. RGB-D Image Alignment Section introduced a joint photometric and geometric objective
More informationLearning-based Localization
Learning-based Localization Eric Brachmann ECCV 2018 Tutorial on Visual Localization - Feature-based vs. Learned Approaches Torsten Sattler, Eric Brachmann Roadmap Machine Learning Basics [10min] Convolutional
More informationScanning and Printing Objects in 3D Jürgen Sturm
Scanning and Printing Objects in 3D Jürgen Sturm Metaio (formerly Technical University of Munich) My Research Areas Visual navigation for mobile robots RoboCup Kinematic Learning Articulated Objects Quadrocopters
More informationFaster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun Presented by Tushar Bansal Objective 1. Get bounding box for all objects
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 informationModels Matter, So Does Training: An Empirical Study of CNNs for Optical Flow Estimation
1 Models Matter, So Does Training: An Empirical Study of CNNs for Optical Flow Estimation Deqing Sun, Xiaodong Yang, Ming-Yu Liu, and Jan Kautz arxiv:1809.05571v1 [cs.cv] 14 Sep 2018 Abstract We investigate
More informationDeep Supervision with Shape Concepts for Occlusion-Aware 3D Object Parsing
Deep Supervision with Shape Concepts for Occlusion-Aware 3D Object Parsing Supplementary Material Introduction In this supplementary material, Section 2 details the 3D annotation for CAD models and real
More informationPart II: Modeling Aspects
Yosemite test sequence Illumination changes Motion discontinuities Variational Optical Flow Estimation Part II: Modeling Aspects Discontinuity Di ti it preserving i smoothness th tterms Robust data terms
More informationarxiv: v2 [cs.cv] 21 Feb 2018
UnDeepVO: Monocular Visual Odometry through Unsupervised Deep Learning Ruihao Li 1, Sen Wang 2, Zhiqiang Long 3 and Dongbing Gu 1 arxiv:1709.06841v2 [cs.cv] 21 Feb 2018 Abstract We propose a novel monocular
More informationUnFlow: Unsupervised Learning of Optical Flow with a Bidirectional Census Loss
UnFlow: Unsupervised Learning of Optical Flow with a Bidirectional Census Loss AAAI 2018, New Orleans, USA Simon Meister, Junhwa Hur, and Stefan Roth Department of Computer Science, TU Darmstadt 2 Deep
More information視覚情報処理論. (Visual Information Processing ) 開講所属 : 学際情報学府水 (Wed)5 [16:50-18:35]
視覚情報処理論 (Visual Information Processing ) 開講所属 : 学際情報学府水 (Wed)5 [16:50-18:35] Computer Vision Design algorithms to implement the function of human vision 3D reconstruction from 2D image (retinal image)
More informationSuper-Resolution Keyframe Fusion for 3D Modeling with High-Quality Textures
Super-Resolution Keyframe Fusion for 3D Modeling with High-Quality Textures Robert Maier, Jörg Stückler, Daniel Cremers International Conference on 3D Vision (3DV) October 2015, Lyon, France Motivation
More informationVisual-Inertial Localization and Mapping for Robot Navigation
Visual-Inertial Localization and Mapping for Robot Navigation Dr. Guillermo Gallego Robotics & Perception Group University of Zurich Davide Scaramuzza University of Zurich - http://rpg.ifi.uzh.ch Mocular,
More informationMulti-view 3D Models from Single Images with a Convolutional Network
Multi-view 3D Models from Single Images with a Convolutional Network Maxim Tatarchenko University of Freiburg Skoltech - 2nd Christmas Colloquium on Computer Vision Humans have prior knowledge about 3D
More informationarxiv: v2 [cs.cv] 7 Oct 2018
Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation Anurag Ranjan 1 Varun Jampani 2 arxiv:1805.09806v2 [cs.cv] 7 Oct 2018 Kihwan Kim 2 Deqing
More informationMask R-CNN. presented by Jiageng Zhang, Jingyao Zhan, Yunhan Ma
Mask R-CNN presented by Jiageng Zhang, Jingyao Zhan, Yunhan Ma Mask R-CNN Background Related Work Architecture Experiment Mask R-CNN Background Related Work Architecture Experiment Background From left
More informationOcclusions, Motion and Depth Boundaries with a Generic Network for Disparity, Optical Flow or Scene Flow Estimation
Occlusions, Motion and Depth Boundaries with a Generic Network for Disparity, Optical Flow or Scene Flow Estimation Eddy Ilg *, Tonmoy Saikia *, Margret Keuper, and Thomas Brox University of Freiburg,
More informationMulti-stable Perception. Necker Cube
Multi-stable Perception Necker Cube Spinning dancer illusion, Nobuyuki Kayahara Multiple view geometry Stereo vision Epipolar geometry Lowe Hartley and Zisserman Depth map extraction Essential matrix
More information(Deep) Learning for Robot Perception and Navigation. Wolfram Burgard
(Deep) Learning for Robot Perception and Navigation Wolfram Burgard Deep Learning for Robot Perception (and Navigation) Lifeng Bo, Claas Bollen, Thomas Brox, Andreas Eitel, Dieter Fox, Gabriel L. Oliveira,
More informationLearning with Side Information through Modality Hallucination
Master Seminar Report for Recent Trends in 3D Computer Vision Learning with Side Information through Modality Hallucination Judy Hoffman, Saurabh Gupta, Trevor Darrell. CVPR 2016 Nan Yang Supervisor: Benjamin
More informationScanning and Printing Objects in 3D
Scanning and Printing Objects in 3D Dr. Jürgen Sturm metaio GmbH (formerly Technical University of Munich) My Research Areas Visual navigation for mobile robots RoboCup Kinematic Learning Articulated Objects
More informationVol agile avec des micro-robots volants contrôlés par vision
Vol agile avec des micro-robots volants contrôlés par vision From Active Perception to Event-based Vision Henri Rebecq from Prof. Davide Scaramuzza s lab GT UAV 17 Novembre 2016, Paris Davide Scaramuzza
More informationarxiv: v1 [cs.cv] 16 Nov 2015
Coarse-to-fine Face Alignment with Multi-Scale Local Patch Regression Zhiao Huang hza@megvii.com Erjin Zhou zej@megvii.com Zhimin Cao czm@megvii.com arxiv:1511.04901v1 [cs.cv] 16 Nov 2015 Abstract Facial
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 informationStep-by-Step Model Buidling
Step-by-Step Model Buidling Review Feature selection Feature selection Feature correspondence Camera Calibration Euclidean Reconstruction Landing Augmented Reality Vision Based Control Sparse Structure
More informationTeam G-RMI: Google Research & Machine Intelligence
Team G-RMI: Google Research & Machine Intelligence Alireza Fathi (alirezafathi@google.com) Nori Kanazawa, Kai Yang, George Papandreou, Tyler Zhu, Jonathan Huang, Vivek Rathod, Chen Sun, Kevin Murphy, et
More informationDeMoN: Depth and Motion Network for Learning Monocular Stereo Supplementary Material
Learning rate : Depth and Motion Network for Learning Monocular Stereo Supplementary Material A. Network Architecture Details Our network is a chain of encoder-decoder networks. Figures 15 and 16 explain
More informationCVPR 2014 Visual SLAM Tutorial Kintinuous
CVPR 2014 Visual SLAM Tutorial Kintinuous kaess@cmu.edu The Robotics Institute Carnegie Mellon University Recap: KinectFusion [Newcombe et al., ISMAR 2011] RGB-D camera GPU 3D/color model RGB TSDF (volumetric
More informationFast Odometry and Scene Flow from RGB-D Cameras based on Geometric Clustering
Fast Odometry and Scene Flow from RGB-D Cameras based on Geometric Clustering Mariano Jaimez 1,2, Christian Kerl 2, Javier Gonzalez-Jimenez 1 and Daniel Cremers 2 Abstract In this paper we propose an efficient
More informationSingle-shot Extrinsic Calibration of a Generically Configured RGB-D Camera Rig from Scene Constraints
Single-shot Extrinsic Calibration of a Generically Configured RGB-D Camera Rig from Scene Constraints Jiaolong Yang*, Yuchao Dai^, Hongdong Li^, Henry Gardner^ and Yunde Jia* *Beijing Institute of Technology
More informationGeometric Reconstruction Dense reconstruction of scene geometry
Lecture 5. Dense Reconstruction and Tracking with Real-Time Applications Part 2: Geometric Reconstruction Dr Richard Newcombe and Dr Steven Lovegrove Slide content developed from: [Newcombe, Dense Visual
More informationThe Hilbert Problems of Computer Vision. Jitendra Malik UC Berkeley & Google, Inc.
The Hilbert Problems of Computer Vision Jitendra Malik UC Berkeley & Google, Inc. This talk The computational power of the human brain Research is the art of the soluble Hilbert problems, circa 2004 Hilbert
More informationAn Automatic Method for Adjustment of a Camera Calibration Room
An Automatic Method for Adjustment of a Camera Calibration Room Presented at the FIG Working Week 2017, May 29 - June 2, 2017 in Helsinki, Finland Theory, algorithms, implementation, and two advanced applications.
More informationDeep Supervision with Shape Concepts for Occlusion-Aware 3D Object Parsing Supplementary Material
Deep Supervision with Shape Concepts for Occlusion-Aware 3D Object Parsing Supplementary Material Chi Li, M. Zeeshan Zia 2, Quoc-Huy Tran 2, Xiang Yu 2, Gregory D. Hager, and Manmohan Chandraker 2 Johns
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 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 informationJoint Optical Flow and Temporally Consistent Semantic Segmentation
Joint Optical Flow and Temporally Consistent Semantic Segmentation Junhwa Hur and Stefan Roth Department of Computer Science, TU Darmstadt Abstract. The importance and demands of visual scene understanding
More informationYiqi Yan. May 10, 2017
Yiqi Yan May 10, 2017 P a r t I F u n d a m e n t a l B a c k g r o u n d s Convolution Single Filter Multiple Filters 3 Convolution: case study, 2 filters 4 Convolution: receptive field receptive field
More informationFrom 3D descriptors to monocular 6D pose: what have we learned?
ECCV Workshop on Recovering 6D Object Pose From 3D descriptors to monocular 6D pose: what have we learned? Federico Tombari CAMP - TUM Dynamic occlusion Low latency High accuracy, low jitter No expensive
More informationAUTOMATIC 3D HUMAN ACTION RECOGNITION Ajmal Mian Associate Professor Computer Science & Software Engineering
AUTOMATIC 3D HUMAN ACTION RECOGNITION Ajmal Mian Associate Professor Computer Science & Software Engineering www.csse.uwa.edu.au/~ajmal/ Overview Aim of automatic human action recognition Applications
More informationCollaborative Mapping with Streetlevel Images in the Wild. Yubin Kuang Co-founder and Computer Vision Lead
Collaborative Mapping with Streetlevel Images in the Wild Yubin Kuang Co-founder and Computer Vision Lead Mapillary Mapillary is a street-level imagery platform, powered by collaboration and computer vision.
More informationLost! Leveraging the Crowd for Probabilistic Visual Self-Localization
Lost! Leveraging the Crowd for Probabilistic Visual Self-Localization Marcus A. Brubaker (Toyota Technological Institute at Chicago) Andreas Geiger (Karlsruhe Institute of Technology & MPI Tübingen) Raquel
More informationObject detection with CNNs
Object detection with CNNs 80% PASCAL VOC mean0average0precision0(map) 70% 60% 50% 40% 30% 20% 10% Before CNNs After CNNs 0% 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 year Region proposals
More informationTracking. Hao Guan( 管皓 ) School of Computer Science Fudan University
Tracking Hao Guan( 管皓 ) School of Computer Science Fudan University 2014-09-29 Multimedia Video Audio Use your eyes Video Tracking Use your ears Audio Tracking Tracking Video Tracking Definition Given
More informationarxiv: v1 [cs.cv] 11 Apr 2016
Beyond Brightness Constancy: Learning Noise Models for Optical Flow arxiv:1604.02815v1 [cs.cv] 11 Apr 2016 Dan Rosenbaum School of Computer Science and Engineering Hebrew University of Jerusalem www.cs.huji.ac.il/
More informationMotion Cooperation: Smooth Piece-Wise Rigid Scene Flow from RGB-D Images
Motion Cooperation: Smooth Piece-Wise Rigid Scene Flow from RGB-D Images Mariano Jaimez1,2 Mohamed Souiai1 Jo rg Stu ckler1 Javier Gonzalez-Jimenez2 Daniel Cremers1 1 Technische Universita t Mu nchen,
More informationarxiv: v1 [cs.cv] 30 Nov 2017
Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation Huaizu Jiang 1 Deqing Sun 2 Varun Jampani 2 Ming-Hsuan Yang 3,2 Erik Learned-Miller 1 Jan Kautz 2 1 UMass Amherst
More informationExploiting Semantic Information and Deep Matching for Optical Flow
Exploiting Semantic Information and Deep Matching for Optical Flow Min Bai, Wenjie Luo, Kaustav Kundu, Raquel Urtasun Department of Computer Science, University of Toronto {mbai, wenjie, kkundu, urtasun}@cs.toronto.edu
More information3D Scene Reconstruction with a Mobile Camera
3D Scene Reconstruction with a Mobile Camera 1 Introduction Robert Carrera and Rohan Khanna Stanford University: CS 231A Autonomous supernumerary arms, or "third arms", while still unconventional, hold
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 informationHuman Detection and Tracking for Video Surveillance: A Cognitive Science Approach
Human Detection and Tracking for Video Surveillance: A Cognitive Science Approach Vandit Gajjar gajjar.vandit.381@ldce.ac.in Ayesha Gurnani gurnani.ayesha.52@ldce.ac.in Yash Khandhediya khandhediya.yash.364@ldce.ac.in
More informationPeripheral drift illusion
Peripheral drift illusion Does it work on other animals? Computer Vision Motion and Optical Flow Many slides adapted from J. Hays, S. Seitz, R. Szeliski, M. Pollefeys, K. Grauman and others Video A video
More informationPWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume
: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume Deqing Sun, Xiaodong Yang, Ming-Yu Liu, and Jan Kautz NVIDIA Abstract We present a compact but effective CNN model for optical flow, called.
More informationSURVEY OF LOCAL AND GLOBAL OPTICAL FLOW WITH COARSE TO FINE METHOD
SURVEY OF LOCAL AND GLOBAL OPTICAL FLOW WITH COARSE TO FINE METHOD M.E-II, Department of Computer Engineering, PICT, Pune ABSTRACT: Optical flow as an image processing technique finds its applications
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 information3D reconstruction how accurate can it be?
Performance Metrics for Correspondence Problems 3D reconstruction how accurate can it be? Pierre Moulon, Foxel CVPR 2015 Workshop Boston, USA (June 11, 2015) We can capture large environments. But for
More informationFLaME: Fast Lightweight Mesh Estimation using Variational Smoothing on Delaunay Graphs
FLaME: Fast Lightweight Mesh Estimation using Variational Smoothing on Delaunay Graphs W. Nicholas Greene Robust Robotics Group, MIT CSAIL LPM Workshop IROS 2017 September 28, 2017 with Nicholas Roy 1
More informationPL-SVO: Semi-Direct Monocular Visual Odometry by Combining Points and Line Segments
2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) Daejeon Convention Center October 9-14, 2016, Daejeon, Korea PL-SVO: Semi-Direct Monocular Visual Odometry by Combining Points
More informationIntroduction to Deep Learning for Facial Understanding Part III: Regional CNNs
Introduction to Deep Learning for Facial Understanding Part III: Regional CNNs Raymond Ptucha, Rochester Institute of Technology, USA Tutorial-9 May 19, 218 www.nvidia.com/dli R. Ptucha 18 1 Fair Use Agreement
More informationDynamic Shape Tracking via Region Matching
Dynamic Shape Tracking via Region Matching Ganesh Sundaramoorthi Asst. Professor of EE and AMCS KAUST (Joint work with Yanchao Yang) The Problem: Shape Tracking Given: exact object segmentation in frame1
More informationSynscapes A photorealistic syntehtic dataset for street scene parsing Jonas Unger Department of Science and Technology Linköpings Universitet.
Synscapes A photorealistic syntehtic dataset for street scene parsing Jonas Unger Department of Science and Technology Linköpings Universitet 7D Labs VINNOVA https://7dlabs.com Photo-realistic image synthesis
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 informationAugmented Reality, Advanced SLAM, Applications
Augmented Reality, Advanced SLAM, Applications Prof. Didier Stricker & Dr. Alain Pagani alain.pagani@dfki.de Lecture 3D Computer Vision AR, SLAM, Applications 1 Introduction Previous lectures: Basics (camera,
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 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 informationSpatial Localization and Detection. Lecture 8-1
Lecture 8: Spatial Localization and Detection Lecture 8-1 Administrative - Project Proposals were due on Saturday Homework 2 due Friday 2/5 Homework 1 grades out this week Midterm will be in-class on Wednesday
More informationTri-modal Human Body Segmentation
Tri-modal Human Body Segmentation Master of Science Thesis Cristina Palmero Cantariño Advisor: Sergio Escalera Guerrero February 6, 2014 Outline 1 Introduction 2 Tri-modal dataset 3 Proposed baseline 4
More informationSrikumar Ramalingam. Review. 3D Reconstruction. Pose Estimation Revisited. School of Computing University of Utah
School of Computing University of Utah Presentation Outline 1 2 3 Forward Projection (Reminder) u v 1 KR ( I t ) X m Y m Z m 1 Backward Projection (Reminder) Q K 1 q Q K 1 u v 1 What is pose estimation?
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 informationSelf Driving. DNN * * Reinforcement * Unsupervised *
CNN 응용 Methods Traditional Deep-Learning based Non-machine Learning Machine-Learning based method Supervised SVM MLP CNN RNN (LSTM) Localizati on GPS, SLAM Self Driving Perception Pedestrian detection
More informationTowards a Simulation Driven Stereo Vision System
Towards a Simulation Driven Stereo Vision System Martin Peris Cyberdyne Inc., Japan Email: martin peris@cyberdyne.jp Sara Martull University of Tsukuba, Japan Email: info@martull.com Atsuto Maki Toshiba
More information