Multi-View Stereo for Static and Dynamic Scenes

Size: px
Start display at page:

Download "Multi-View Stereo for Static and Dynamic Scenes"

Transcription

1 Multi-View Stereo for Static and Dynamic Scenes Wolfgang Burgard Jan 6, 2010 Main references Yasutaka Furukawa and Jean Ponce, Accurate, Dense and Robust Multi-View Stereopsis, 2007 C.L. Zitnick, S.B. Kang, M. Uyttendaele, S. Winder, and R. Szeliski, High-quality Video View Interpolation using a Layered Representation, 2004

2 Stereo Reconstruction - Static Scene Settings Two images (2D) of the same scene Static: Scene hasn't changed accross images Acquisition from different viewpoints Camera parameters known / estimated (Zhang) Goal Reconstruct geometry (3D) of objects in scene... 2

3 Reconstruction so far Visual hull Silhouette based: Intersection of cones from silhouette back projection Image based: Project entrance/exit interval in reference images onto viewing-rays Problem: Concave surface, Image-based: View-dependent 3

4 Epipolar Geometry Scene point Image plane Epipolar Line Depth Baseline (Length b) Optical center Approach Identify correspondences between images ( correspondence problem ) Triangulation: Rays through corresponding pixels x l and x r meet at scene point depth= b focal_length disparity with disparity=x l x r 4

5 Static Scene Approach Overview Idea: Major steps Correspondences of pixels within a local area constrain each other (Local photometric consistency) Geometry as patch set Global visibility constraints Match features sparse surface patches Expand to nearby pixels dense set of patches Filter out incorrect patches ( visibility ) Patch model -> mesh 5

6 Initial Patch Set (Match step) 1/2 Divide image into 32x32 pixel cells Extract features in each cell Blobs ( DoG operator ) Corner ( Harris operator ) Uniform coverage: 4 local maxima with strongest response of each operator Triangulation with feature pairs (f,f') => 3D points Tolerance of 2 pixels from epipolar line Consider matches (f,f') if of same type 6

7 Initial Patch Set (Match step) 2/2 Many 3D points for feature f. Optimal one? Nearest to O which is photoconsistent: Patch candidate p Center c(p): 3D point Extension of p: normal Projection into image in 5x5 (7x7) axis aligned square Optimiziation consistent Maximal patches photometric consistency Refine parameters: c(p) and n(p) p photoconsistent with 2-3 images Accept, otherwise next 3D point optical center O inconsistent patch 7

8 Photometric Consistency p photoconsistent with image I? Reference image Normalized cross corelation (NCC) Energy independent similarity measure Similarity of p in I with p in reference image NCC > treshold => photoconsistent Correspondence problem not solved pointwise but for an area Local surface area considered perspectively 8

9 Expand 1/2 Initial patches too sparse For all patches p add patches p' to neighbour cells Conditions for adding No visible patch in cell No should-be-visible patch n-adjacent in cell patch p p's neighbour Close patch centers patch p p's neighbour Similar normals 9

10 Expand 2/2 Initial parameters of new patch p' n(p') = n(p) c(p') intersection of ray through Cell (i',j') with plane of p neighbour patch p' plane of p Optimiziation Maximal photometric consistency Refines c(p') and n(p') Accept if photometric consistent in 2-3 images 10

11 Filter 1/2 Remove patches outside of real surface Caused by e.g. obstacles outlier seen in one image conflicts 2 patches seen in other images Condition to remove p: p's Photometric consistency < photometric consistency of patches hidden by p Intuition: Projected outliers visible in less images than real surface patches 11

12 Filter 2/2 Remove patches inside real surface Caused by iterative scheme ( expand ) Patch added occludes "inside patch Not visible in 2-3 images => remove p Visibility here defined via depth values outlier only visible in 1 image 12

13 Mesh from Patches 1/2 Once Match (initial patches) Expand and Filter step until convergence (dense patches) Mesh from patches Initial bounding volume mesh Move vertices by forces Remesh 13

14 Mesh from Patches 2/2 Forces moving vertices Smoothness - regularization (rigidness of mesh ) Photometric consistency Initial phase: Move towards photoconsistent patches Later phases: Create patch at vertex; Optimize patch; Photoconsistency: c(p) - c*(p) Rim consistency - pull mesh towards visual cone projected surface silhouette ~ silhouette in image 14

15 Results Computation Time: Minutes to hours 15

16 Multi-View Stereo for Dynamic Scenes Input Goal: Image sequences (video) of dynamic scene Each sequence captured scene over time Variable viewpoints in video ( using geometric data ) Additional challenges: Object Movement Object Deformation Much data ( input and output ) Scene New viewpoint between recording cameras 16

17 Viewpoint Manipulation Approaches 1/2 Geometry-less approaches Jump between still cameras No software interpolation Problem: Jumping artifacts Scene Still cameras along trajectory 17

18 Viewpoint Manipulation Approaches 1/2 Geometry-less approaches Jump between still cameras No software interpolation Problem: Jumping artifacts Scene Still cameras along trajectory 18

19 Viewpoint Manipulation Approaches 1/2 Geometry-less approaches Jump between still cameras No software interpolation Problem: Jumping artifacts Scene Still cameras along trajectory 19

20 Viewpoint Manipulation Approaches 2/2 'Light-field Rendering' for dynamic scences Problem: Requires many videos Homography Project & Blend Novel view Problem: No parallax effect, i.e. foreground and background objects move with same velocity - independent from depth 20

21 Overview Snchronized videos + Camera parameters 3D Reconstruction with Image Segmentation Matte extraction ( depth disconuity artifacts ) Offline Compression Rendering using temporal two layered compression representation Interactively 21

22 Recording Setup 8 synchronized cameras 1024x fps 30 Basic camera setup Possible extension: 2D or 360 not trivial, e.g. cameras in image 2D camera setup Zhang's algorithm to estimate camera parameters 22

23 Stereo Reconstruction 1/2 Traditional 3D Stereo Reconstruction Errors around disparity disconuities => noticable visual artifacts at intensity edges Color segmentation-based stereo algorithm Segment image Similar disparity in each segment => no artifacts 1. Smooth & reduce noise 2. Merge segments (initially: each pixel ) if average color similar 3. Split/merge too large/small segments Segments 23

24 Stereo Reconstruction 2/2 Initial disparity in each segment Photometric conditions Constant disparity Refine disparity Relax constant assumption Average across images Average between segments Smoothness in each segment 24

25 Boundary Matting 1/4 Problem: At depth disconuities: Foreground pixels contain background color background foreground Hairs from foreground object having blue color from background Pixel contain foreground and background color 25

26 Boundary Matting 2/4 Left camera image Right camera image Novel view 26

27 Boundary Matting 3/4 Matting at disparity disconuities Extract foreground and background colors + alpha Two-layered representation Main layer Main layer colors Main layer depth 27

28 Boundary Matting 4/4 Matting at disparity disconuities Extract foreground and background colors + alpha Two-layered representation Boundary layer Boundary colors Boundary depth Boundary alpha 28

29 Rendering 1/2 Steps 1.Select 2 nearest cameras 2.Render into 2 buffers separate ( 1 for each camera ) Project main & boundary layer into view Depth map => 3D mesh Remove triangles across depth disconuities from main layer; Boundary mesh instead Main mesh at depth disconuity Boundary mesh at depth disconuity 29

30 Rendering 2/2 3. Blend buffers Pixels with different depth => use frontmost Similar depth => average with camera distance to view as weight Right camera nearer => more influence of pixel colors 30

31 Results Interactive rendering 5 fps 10 fps ATI 9800 PRO If all images on GPU memory: 30 fps 31

32 Summary Static scene approach Stereo reconstuction with features Photoconsistent patches Geometry: Complete 3D patch & mesh model Dynamic scene approach Stereo reconstruction with segmented images Geometry: 2 layers: Main layer + boundary layer ( matting ) 3D mesh for rendering 32

33 Discussion 33

Multi-view stereo. Many slides adapted from S. Seitz

Multi-view stereo. Many slides adapted from S. Seitz Multi-view stereo Many slides adapted from S. Seitz Beyond two-view stereo The third eye can be used for verification Multiple-baseline stereo Pick a reference image, and slide the corresponding window

More information

Dense 3D Reconstruction. Christiano Gava

Dense 3D Reconstruction. Christiano Gava Dense 3D Reconstruction Christiano Gava christiano.gava@dfki.de Outline Previous lecture: structure and motion II Structure and motion loop Triangulation Today: dense 3D reconstruction The matching problem

More information

Dense 3D Reconstruction. Christiano Gava

Dense 3D Reconstruction. Christiano Gava Dense 3D Reconstruction Christiano Gava christiano.gava@dfki.de Outline Previous lecture: structure and motion II Structure and motion loop Triangulation Wide baseline matching (SIFT) Today: dense 3D reconstruction

More information

Image Based Reconstruction II

Image Based Reconstruction II Image Based Reconstruction II Qixing Huang Feb. 2 th 2017 Slide Credit: Yasutaka Furukawa Image-Based Geometry Reconstruction Pipeline Last Lecture: Multi-View SFM Multi-View SFM This Lecture: Multi-View

More information

But, vision technology falls short. and so does graphics. Image Based Rendering. Ray. Constant radiance. time is fixed. 3D position 2D direction

But, vision technology falls short. and so does graphics. Image Based Rendering. Ray. Constant radiance. time is fixed. 3D position 2D direction Computer Graphics -based rendering Output Michael F. Cohen Microsoft Research Synthetic Camera Model Computer Vision Combined Output Output Model Real Scene Synthetic Camera Model Real Cameras Real Scene

More information

EE795: Computer Vision and Intelligent Systems

EE795: Computer Vision and Intelligent Systems EE795: Computer Vision and Intelligent Systems Spring 2012 TTh 17:30-18:45 FDH 204 Lecture 14 130307 http://www.ee.unlv.edu/~b1morris/ecg795/ 2 Outline Review Stereo Dense Motion Estimation Translational

More information

Volumetric stereo with silhouette and feature constraints

Volumetric stereo with silhouette and feature constraints Volumetric stereo with silhouette and feature constraints Jonathan Starck, Gregor Miller and Adrian Hilton Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, GU2 7XH, UK.

More information

PERFORMANCE CAPTURE FROM SPARSE MULTI-VIEW VIDEO

PERFORMANCE CAPTURE FROM SPARSE MULTI-VIEW VIDEO Stefan Krauß, Juliane Hüttl SE, SoSe 2011, HU-Berlin PERFORMANCE CAPTURE FROM SPARSE MULTI-VIEW VIDEO 1 Uses of Motion/Performance Capture movies games, virtual environments biomechanics, sports science,

More information

Multiple View Geometry

Multiple View Geometry Multiple View Geometry Martin Quinn with a lot of slides stolen from Steve Seitz and Jianbo Shi 15-463: Computational Photography Alexei Efros, CMU, Fall 2007 Our Goal The Plenoptic Function P(θ,φ,λ,t,V

More information

Multi-View 3D-Reconstruction

Multi-View 3D-Reconstruction Multi-View 3D-Reconstruction Cedric Cagniart Computer Aided Medical Procedures (CAMP) Technische Universität München, Germany 1 Problem Statement Given several calibrated views of an object... can we automatically

More information

Step-by-Step Model Buidling

Step-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 information

3D Computer Vision. Dense 3D Reconstruction II. Prof. Didier Stricker. Christiano Gava

3D Computer Vision. Dense 3D Reconstruction II. Prof. Didier Stricker. Christiano Gava 3D Computer Vision Dense 3D Reconstruction II Prof. Didier Stricker Christiano Gava Kaiserlautern University http://ags.cs.uni-kl.de/ DFKI Deutsches Forschungszentrum für Künstliche Intelligenz http://av.dfki.de

More information

Chaplin, Modern Times, 1936

Chaplin, Modern Times, 1936 Chaplin, Modern Times, 1936 [A Bucket of Water and a Glass Matte: Special Effects in Modern Times; bonus feature on The Criterion Collection set] Multi-view geometry problems Structure: Given projections

More information

Geometric Reconstruction Dense reconstruction of scene geometry

Geometric 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 information

Fundamentals of Stereo Vision Michael Bleyer LVA Stereo Vision

Fundamentals of Stereo Vision Michael Bleyer LVA Stereo Vision Fundamentals of Stereo Vision Michael Bleyer LVA Stereo Vision What Happened Last Time? Human 3D perception (3D cinema) Computational stereo Intuitive explanation of what is meant by disparity Stereo matching

More information

3D Reconstruction of Dynamic Textures with Crowd Sourced Data. Dinghuang Ji, Enrique Dunn and Jan-Michael Frahm

3D Reconstruction of Dynamic Textures with Crowd Sourced Data. Dinghuang Ji, Enrique Dunn and Jan-Michael Frahm 3D Reconstruction of Dynamic Textures with Crowd Sourced Data Dinghuang Ji, Enrique Dunn and Jan-Michael Frahm 1 Background Large scale scene reconstruction Internet imagery 3D point cloud Dense geometry

More information

Processing 3D Surface Data

Processing 3D Surface Data Processing 3D Surface Data Computer Animation and Visualisation Lecture 17 Institute for Perception, Action & Behaviour School of Informatics 3D Surfaces 1 3D surface data... where from? Iso-surfacing

More information

Using Shape Priors to Regularize Intermediate Views in Wide-Baseline Image-Based Rendering

Using Shape Priors to Regularize Intermediate Views in Wide-Baseline Image-Based Rendering Using Shape Priors to Regularize Intermediate Views in Wide-Baseline Image-Based Rendering Cédric Verleysen¹, T. Maugey², P. Frossard², C. De Vleeschouwer¹ ¹ ICTEAM institute, UCL (Belgium) ; ² LTS4 lab,

More information

Stereo Vision. MAN-522 Computer Vision

Stereo Vision. MAN-522 Computer Vision Stereo Vision MAN-522 Computer Vision What is the goal of stereo vision? The recovery of the 3D structure of a scene using two or more images of the 3D scene, each acquired from a different viewpoint in

More information

3D Photography: Stereo Matching

3D Photography: Stereo Matching 3D Photography: Stereo Matching Kevin Köser, Marc Pollefeys Spring 2012 http://cvg.ethz.ch/teaching/2012spring/3dphoto/ Stereo & Multi-View Stereo Tsukuba dataset http://cat.middlebury.edu/stereo/ Stereo

More information

Augmented and Mixed Reality

Augmented and Mixed Reality Augmented and Mixed Reality Uma Mudenagudi Dept. of Computer Science and Engineering, Indian Institute of Technology Delhi Outline Introduction to Augmented Reality(AR) and Mixed Reality(MR) A Typical

More information

CS 4495 Computer Vision A. Bobick. Motion and Optic Flow. Stereo Matching

CS 4495 Computer Vision A. Bobick. Motion and Optic Flow. Stereo Matching Stereo Matching Fundamental matrix Let p be a point in left image, p in right image l l Epipolar relation p maps to epipolar line l p maps to epipolar line l p p Epipolar mapping described by a 3x3 matrix

More information

Multiple View Geometry

Multiple View Geometry Multiple View Geometry CS 6320, Spring 2013 Guest Lecture Marcel Prastawa adapted from Pollefeys, Shah, and Zisserman Single view computer vision Projective actions of cameras Camera callibration Photometric

More information

What have we leaned so far?

What have we leaned so far? What have we leaned so far? Camera structure Eye structure Project 1: High Dynamic Range Imaging What have we learned so far? Image Filtering Image Warping Camera Projection Model Project 2: Panoramic

More information

Shape from Silhouettes I

Shape from Silhouettes I Shape from Silhouettes I Guido Gerig CS 6320, Spring 2015 Credits: Marc Pollefeys, UNC Chapel Hill, some of the figures and slides are also adapted from J.S. Franco, J. Matusik s presentations, and referenced

More information

Computer Vision Lecture 17

Computer Vision Lecture 17 Computer Vision Lecture 17 Epipolar Geometry & Stereo Basics 13.01.2015 Bastian Leibe RWTH Aachen http://www.vision.rwth-aachen.de leibe@vision.rwth-aachen.de Announcements Seminar in the summer semester

More information

A virtual tour of free viewpoint rendering

A virtual tour of free viewpoint rendering A virtual tour of free viewpoint rendering Cédric Verleysen ICTEAM institute, Université catholique de Louvain, Belgium cedric.verleysen@uclouvain.be Organization of the presentation Context Acquisition

More information

Computer Vision Lecture 17

Computer Vision Lecture 17 Announcements Computer Vision Lecture 17 Epipolar Geometry & Stereo Basics Seminar in the summer semester Current Topics in Computer Vision and Machine Learning Block seminar, presentations in 1 st week

More information

Rendering. Converting a 3D scene to a 2D image. Camera. Light. Rendering. View Plane

Rendering. Converting a 3D scene to a 2D image. Camera. Light. Rendering. View Plane Rendering Pipeline Rendering Converting a 3D scene to a 2D image Rendering Light Camera 3D Model View Plane Rendering Converting a 3D scene to a 2D image Basic rendering tasks: Modeling: creating the world

More information

CSE 252B: Computer Vision II

CSE 252B: Computer Vision II CSE 252B: Computer Vision II Lecturer: Serge Belongie Scribes: Jeremy Pollock and Neil Alldrin LECTURE 14 Robust Feature Matching 14.1. Introduction Last lecture we learned how to find interest points

More information

Processing 3D Surface Data

Processing 3D Surface Data Processing 3D Surface Data Computer Animation and Visualisation Lecture 12 Institute for Perception, Action & Behaviour School of Informatics 3D Surfaces 1 3D surface data... where from? Iso-surfacing

More information

Stereo. Outline. Multiple views 3/29/2017. Thurs Mar 30 Kristen Grauman UT Austin. Multi-view geometry, matching, invariant features, stereo vision

Stereo. Outline. Multiple views 3/29/2017. Thurs Mar 30 Kristen Grauman UT Austin. Multi-view geometry, matching, invariant features, stereo vision Stereo Thurs Mar 30 Kristen Grauman UT Austin Outline Last time: Human stereopsis Epipolar geometry and the epipolar constraint Case example with parallel optical axes General case with calibrated cameras

More information

Omni-directional Multi-baseline Stereo without Similarity Measures

Omni-directional Multi-baseline Stereo without Similarity Measures Omni-directional Multi-baseline Stereo without Similarity Measures Tomokazu Sato and Naokazu Yokoya Graduate School of Information Science, Nara Institute of Science and Technology 8916-5 Takayama, Ikoma,

More information

Hybrid Rendering for Collaborative, Immersive Virtual Environments

Hybrid Rendering for Collaborative, Immersive Virtual Environments Hybrid Rendering for Collaborative, Immersive Virtual Environments Stephan Würmlin wuermlin@inf.ethz.ch Outline! Rendering techniques GBR, IBR and HR! From images to models! Novel view generation! Putting

More information

Visual Shapes of Silhouette Sets

Visual Shapes of Silhouette Sets Visual Shapes of Silhouette Sets Jean-Sébastien Franco Marc Lapierre Edmond Boyer GRAVIR INRIA Rhône-Alpes 655, Avenue de l Europe, 38334 Saint Ismier, France {franco,lapierre,eboyer}@inrialpes.fr Abstract

More information

L2 Data Acquisition. Mechanical measurement (CMM) Structured light Range images Shape from shading Other methods

L2 Data Acquisition. Mechanical measurement (CMM) Structured light Range images Shape from shading Other methods L2 Data Acquisition Mechanical measurement (CMM) Structured light Range images Shape from shading Other methods 1 Coordinate Measurement Machine Touch based Slow Sparse Data Complex planning Accurate 2

More information

Advanced Shading I: Shadow Rasterization Techniques

Advanced Shading I: Shadow Rasterization Techniques Advanced Shading I: Shadow Rasterization Techniques Shadow Terminology umbra: light totally blocked penumbra: light partially blocked occluder: object blocking light Shadow Terminology umbra: light totally

More information

Image Transfer Methods. Satya Prakash Mallick Jan 28 th, 2003

Image Transfer Methods. Satya Prakash Mallick Jan 28 th, 2003 Image Transfer Methods Satya Prakash Mallick Jan 28 th, 2003 Objective Given two or more images of the same scene, the objective is to synthesize a novel view of the scene from a view point where there

More information

Computer Vision I. Dense Stereo Correspondences. Anita Sellent 1/15/16

Computer 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 information

Shape from Silhouettes I

Shape from Silhouettes I Shape from Silhouettes I Guido Gerig CS 6320, Spring 2013 Credits: Marc Pollefeys, UNC Chapel Hill, some of the figures and slides are also adapted from J.S. Franco, J. Matusik s presentations, and referenced

More information

CS 4495 Computer Vision A. Bobick. Motion and Optic Flow. Stereo Matching

CS 4495 Computer Vision A. Bobick. Motion and Optic Flow. Stereo Matching Stereo Matching Fundamental matrix Let p be a point in left image, p in right image l l Epipolar relation p maps to epipolar line l p maps to epipolar line l p p Epipolar mapping described by a 3x3 matrix

More information

Rendering Grass Terrains in Real-Time with Dynamic Lighting. Kévin Boulanger, Sumanta Pattanaik, Kadi Bouatouch August 1st 2006

Rendering Grass Terrains in Real-Time with Dynamic Lighting. Kévin Boulanger, Sumanta Pattanaik, Kadi Bouatouch August 1st 2006 Rendering Grass Terrains in Real-Time with Dynamic Lighting Kévin Boulanger, Sumanta Pattanaik, Kadi Bouatouch August 1st 2006 Goal Rendering millions of grass blades, at any distance, in real-time, with:

More information

Motion Analysis. Motion analysis. Now we will talk about. Differential Motion Analysis. Motion analysis. Difference Pictures

Motion Analysis. Motion analysis. Now we will talk about. Differential Motion Analysis. Motion analysis. Difference Pictures Now we will talk about Motion Analysis Motion analysis Motion analysis is dealing with three main groups of motionrelated problems: Motion detection Moving object detection and location. Derivation of

More information

3D Sensing and Reconstruction Readings: Ch 12: , Ch 13: ,

3D Sensing and Reconstruction Readings: Ch 12: , Ch 13: , 3D Sensing and Reconstruction Readings: Ch 12: 12.5-6, Ch 13: 13.1-3, 13.9.4 Perspective Geometry Camera Model Stereo Triangulation 3D Reconstruction by Space Carving 3D Shape from X means getting 3D coordinates

More information

EECS 442 Computer vision. Stereo systems. Stereo vision Rectification Correspondence problem Active stereo vision systems

EECS 442 Computer vision. Stereo systems. Stereo vision Rectification Correspondence problem Active stereo vision systems EECS 442 Computer vision Stereo systems Stereo vision Rectification Correspondence problem Active stereo vision systems Reading: [HZ] Chapter: 11 [FP] Chapter: 11 Stereo vision P p p O 1 O 2 Goal: estimate

More information

Range Imaging Through Triangulation. Range Imaging Through Triangulation. Range Imaging Through Triangulation. Range Imaging Through Triangulation

Range Imaging Through Triangulation. Range Imaging Through Triangulation. Range Imaging Through Triangulation. Range Imaging Through Triangulation Obviously, this is a very slow process and not suitable for dynamic scenes. To speed things up, we can use a laser that projects a vertical line of light onto the scene. This laser rotates around its vertical

More information

TSBK03 Screen-Space Ambient Occlusion

TSBK03 Screen-Space Ambient Occlusion TSBK03 Screen-Space Ambient Occlusion Joakim Gebart, Jimmy Liikala December 15, 2013 Contents 1 Abstract 1 2 History 2 2.1 Crysis method..................................... 2 3 Chosen method 2 3.1 Algorithm

More information

Model-Based Stereo. Chapter Motivation. The modeling system described in Chapter 5 allows the user to create a basic model of a

Model-Based Stereo. Chapter Motivation. The modeling system described in Chapter 5 allows the user to create a basic model of a 96 Chapter 7 Model-Based Stereo 7.1 Motivation The modeling system described in Chapter 5 allows the user to create a basic model of a scene, but in general the scene will have additional geometric detail

More information

Computer Vision. 3D acquisition

Computer Vision. 3D acquisition è Computer 3D acquisition Acknowledgement Courtesy of Prof. Luc Van Gool 3D acquisition taxonomy s image cannot currently be displayed. 3D acquisition methods Thi passive active uni-directional multi-directional

More information

Ray Casting of Trimmed NURBS Surfaces on the GPU

Ray Casting of Trimmed NURBS Surfaces on the GPU Ray Casting of Trimmed NURBS Surfaces on the GPU Hans-Friedrich Pabst Jan P. Springer André Schollmeyer Robert Lenhardt Christian Lessig Bernd Fröhlich Bauhaus University Weimar Faculty of Media Virtual

More information

Morphable 3D-Mosaics: a Hybrid Framework for Photorealistic Walkthroughs of Large Natural Environments

Morphable 3D-Mosaics: a Hybrid Framework for Photorealistic Walkthroughs of Large Natural Environments Morphable 3D-Mosaics: a Hybrid Framework for Photorealistic Walkthroughs of Large Natural Environments Nikos Komodakis and Georgios Tziritas Computer Science Department, University of Crete E-mails: {komod,

More information

Processing 3D Surface Data

Processing 3D Surface Data Processing 3D Surface Data Computer Animation and Visualisation Lecture 15 Institute for Perception, Action & Behaviour School of Informatics 3D Surfaces 1 3D surface data... where from? Iso-surfacing

More information

CS231A Midterm Review. Friday 5/6/2016

CS231A Midterm Review. Friday 5/6/2016 CS231A Midterm Review Friday 5/6/2016 Outline General Logistics Camera Models Non-perspective cameras Calibration Single View Metrology Epipolar Geometry Structure from Motion Active Stereo and Volumetric

More information

Interpolation using scanline algorithm

Interpolation using scanline algorithm Interpolation using scanline algorithm Idea: Exploit knowledge about already computed color values. Traverse projected triangle top-down using scanline. Compute start and end color value of each pixel

More information

MULTIVIEW stereo (MVS) matching and reconstruction is

MULTIVIEW stereo (MVS) matching and reconstruction is 1362 IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL. 32, NO. 8, AUGUST 2010 Accurate, Dense, and Robust Multiview Stereopsis Yasutaka Furukawa and Jean Ponce, Fellow, IEEE Abstract

More information

Local quadrics surface approximation for real-time tracking of textureless 3D rigid curved objects

Local quadrics surface approximation for real-time tracking of textureless 3D rigid curved objects Local quadrics surface approximation for real-time tracking of textureless 3D rigid curved objects Marina Atsumi Oikawa, Takafumi Taketomi, Goshiro Yamamoto Nara Institute of Science and Technology, Japan

More information

Camera Drones Lecture 3 3D data generation

Camera Drones Lecture 3 3D data generation Camera Drones Lecture 3 3D data generation Ass.Prof. Friedrich Fraundorfer WS 2017 Outline SfM introduction SfM concept Feature matching Camera pose estimation Bundle adjustment Dense matching Data products

More information

Finally: Motion and tracking. Motion 4/20/2011. CS 376 Lecture 24 Motion 1. Video. Uses of motion. Motion parallax. Motion field

Finally: Motion and tracking. Motion 4/20/2011. CS 376 Lecture 24 Motion 1. Video. Uses of motion. Motion parallax. Motion field Finally: Motion and tracking Tracking objects, video analysis, low level motion Motion Wed, April 20 Kristen Grauman UT-Austin Many slides adapted from S. Seitz, R. Szeliski, M. Pollefeys, and S. Lazebnik

More information

Lecture 10 Multi-view Stereo (3D Dense Reconstruction) Davide Scaramuzza

Lecture 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 information

Multiview Reconstruction

Multiview Reconstruction Multiview Reconstruction Why More Than 2 Views? Baseline Too short low accuracy Too long matching becomes hard Why More Than 2 Views? Ambiguity with 2 views Camera 1 Camera 2 Camera 3 Trinocular Stereo

More information

Lecture 14: Basic Multi-View Geometry

Lecture 14: Basic Multi-View Geometry Lecture 14: Basic Multi-View Geometry Stereo If I needed to find out how far point is away from me, I could use triangulation and two views scene point image plane optical center (Graphic from Khurram

More information

Stereo imaging ideal geometry

Stereo imaging ideal geometry Stereo imaging ideal geometry (X,Y,Z) Z f (x L,y L ) f (x R,y R ) Optical axes are parallel Optical axes separated by baseline, b. Line connecting lens centers is perpendicular to the optical axis, and

More information

Player Viewpoint Video Synthesis Using Multiple Cameras

Player Viewpoint Video Synthesis Using Multiple Cameras Player Viewpoint Video Synthesis Using Multiple Cameras Kenji Kimura *, Hideo Saito Department of Information and Computer Science Keio University, Yokohama, Japan * k-kimura@ozawa.ics.keio.ac.jp, saito@ozawa.ics.keio.ac.jp

More information

Calibrated Image Acquisition for Multi-view 3D Reconstruction

Calibrated Image Acquisition for Multi-view 3D Reconstruction Calibrated Image Acquisition for Multi-view 3D Reconstruction Sriram Kashyap M S Guide: Prof. Sharat Chandran Indian Institute of Technology, Bombay April 2009 Sriram Kashyap 3D Reconstruction 1/ 42 Motivation

More information

Scene Segmentation by Color and Depth Information and its Applications

Scene Segmentation by Color and Depth Information and its Applications Scene Segmentation by Color and Depth Information and its Applications Carlo Dal Mutto Pietro Zanuttigh Guido M. Cortelazzo Department of Information Engineering University of Padova Via Gradenigo 6/B,

More information

Talk plan. 3d model. Applications: cultural heritage 5/9/ d shape reconstruction from photographs: a Multi-View Stereo approach

Talk plan. 3d model. Applications: cultural heritage 5/9/ d shape reconstruction from photographs: a Multi-View Stereo approach Talk plan 3d shape reconstruction from photographs: a Multi-View Stereo approach Introduction Multi-View Stereo pipeline Carlos Hernández George Vogiatzis Yasutaka Furukawa Google Aston University Google

More information

Application questions. Theoretical questions

Application questions. Theoretical questions The oral exam will last 30 minutes and will consist of one application question followed by two theoretical questions. Please find below a non exhaustive list of possible application questions. The list

More information

Multi-view Stereo. Ivo Boyadzhiev CS7670: September 13, 2011

Multi-view Stereo. Ivo Boyadzhiev CS7670: September 13, 2011 Multi-view Stereo Ivo Boyadzhiev CS7670: September 13, 2011 What is stereo vision? Generic problem formulation: given several images of the same object or scene, compute a representation of its 3D shape

More information

Multiview Projectors/Cameras System for 3D Reconstruction of Dynamic Scenes

Multiview Projectors/Cameras System for 3D Reconstruction of Dynamic Scenes Multiview Projectors/Cameras System for 3D Reconstruction of Dynamic Scenes Ryo Furukawa Hiroshima City University, Hiroshima, Japan ryo-f@hiroshima-cu.ac.jp Ryusuke Sagawa National Institute of Advanced

More information

Joint 3D-Reconstruction and Background Separation in Multiple Views using Graph Cuts

Joint 3D-Reconstruction and Background Separation in Multiple Views using Graph Cuts Joint 3D-Reconstruction and Background Separation in Multiple Views using Graph Cuts Bastian Goldlücke and Marcus A. Magnor Graphics-Optics-Vision Max-Planck-Institut für Informatik, Saarbrücken, Germany

More information

Stereo Vision II: Dense Stereo Matching

Stereo Vision II: Dense Stereo Matching Stereo Vision II: Dense Stereo Matching Nassir Navab Slides prepared by Christian Unger Outline. Hardware. Challenges. Taxonomy of Stereo Matching. Analysis of Different Problems. Practical Considerations.

More information

IMAGE-BASED RENDERING

IMAGE-BASED RENDERING IMAGE-BASED RENDERING 1. What is Image-Based Rendering? - The synthesis of new views of a scene from pre-recorded pictures.!"$#% "'&( )*+,-/.). #0 1 ' 2"&43+5+, 2. Why? (1) We really enjoy visual magic!

More information

Multiview Depth-Image Compression Using an Extended H.264 Encoder Morvan, Y.; Farin, D.S.; de With, P.H.N.

Multiview Depth-Image Compression Using an Extended H.264 Encoder Morvan, Y.; Farin, D.S.; de With, P.H.N. Multiview Depth-Image Compression Using an Extended H.264 Encoder Morvan, Y.; Farin, D.S.; de With, P.H.N. Published in: Proceedings of the 9th international conference on Advanced Concepts for Intelligent

More information

CS 4620 Midterm, March 21, 2017

CS 4620 Midterm, March 21, 2017 CS 460 Midterm, March 1, 017 This 90-minute exam has 4 questions worth a total of 100 points. Use the back of the pages if you need more space. Academic Integrity is expected of all students of Cornell

More information

Acquisition and Visualization of Colored 3D Objects

Acquisition and Visualization of Colored 3D Objects Acquisition and Visualization of Colored 3D Objects Kari Pulli Stanford University Stanford, CA, U.S.A kapu@cs.stanford.edu Habib Abi-Rached, Tom Duchamp, Linda G. Shapiro and Werner Stuetzle University

More information

Project Updates Short lecture Volumetric Modeling +2 papers

Project Updates Short lecture Volumetric Modeling +2 papers Volumetric Modeling Schedule (tentative) Feb 20 Feb 27 Mar 5 Introduction Lecture: Geometry, Camera Model, Calibration Lecture: Features, Tracking/Matching Mar 12 Mar 19 Mar 26 Apr 2 Apr 9 Apr 16 Apr 23

More information

Final Exam Study Guide CSE/EE 486 Fall 2007

Final Exam Study Guide CSE/EE 486 Fall 2007 Final Exam Study Guide CSE/EE 486 Fall 2007 Lecture 2 Intensity Sufaces and Gradients Image visualized as surface. Terrain concepts. Gradient of functions in 1D and 2D Numerical derivatives. Taylor series.

More information

Image-Based Modeling and Rendering. Image-Based Modeling and Rendering. Final projects IBMR. What we have learnt so far. What IBMR is about

Image-Based Modeling and Rendering. Image-Based Modeling and Rendering. Final projects IBMR. What we have learnt so far. What IBMR is about Image-Based Modeling and Rendering Image-Based Modeling and Rendering MIT EECS 6.837 Frédo Durand and Seth Teller 1 Some slides courtesy of Leonard McMillan, Wojciech Matusik, Byong Mok Oh, Max Chen 2

More information

Projective Surface Refinement for Free-Viewpoint Video

Projective Surface Refinement for Free-Viewpoint Video Projective Surface Refinement for Free-Viewpoint Video Gregor Miller, Jonathan Starck and Adrian Hilton Centre for Vision, Speech and Signal Processing, University of Surrey, UK {Gregor.Miller, J.Starck,

More information

1-2 Feature-Based Image Mosaicing

1-2 Feature-Based Image Mosaicing MVA'98 IAPR Workshop on Machine Vision Applications, Nov. 17-19, 1998, Makuhari, Chibq Japan 1-2 Feature-Based Image Mosaicing Naoki Chiba, Hiroshi Kano, Minoru Higashihara, Masashi Yasuda, and Masato

More information

Lecture 10 Dense 3D Reconstruction

Lecture 10 Dense 3D Reconstruction Institute of Informatics Institute of Neuroinformatics Lecture 10 Dense 3D Reconstruction Davide Scaramuzza 1 REMODE: Probabilistic, Monocular Dense Reconstruction in Real Time M. Pizzoli, C. Forster,

More information

EE795: Computer Vision and Intelligent Systems

EE795: Computer Vision and Intelligent Systems EE795: Computer Vision and Intelligent Systems Spring 2012 TTh 17:30-18:45 FDH 204 Lecture 12 130228 http://www.ee.unlv.edu/~b1morris/ecg795/ 2 Outline Review Panoramas, Mosaics, Stitching Two View Geometry

More information

Recap: Features and filters. Recap: Grouping & fitting. Now: Multiple views 10/29/2008. Epipolar geometry & stereo vision. Why multiple views?

Recap: Features and filters. Recap: Grouping & fitting. Now: Multiple views 10/29/2008. Epipolar geometry & stereo vision. Why multiple views? Recap: Features and filters Epipolar geometry & stereo vision Tuesday, Oct 21 Kristen Grauman UT-Austin Transforming and describing images; textures, colors, edges Recap: Grouping & fitting Now: Multiple

More information

BIL Computer Vision Apr 16, 2014

BIL Computer Vision Apr 16, 2014 BIL 719 - Computer Vision Apr 16, 2014 Binocular Stereo (cont d.), Structure from Motion Aykut Erdem Dept. of Computer Engineering Hacettepe University Slide credit: S. Lazebnik Basic stereo matching algorithm

More information

Shape from Silhouettes II

Shape from Silhouettes II Shape from Silhouettes II Guido Gerig CS 6320, S2013 (slides modified from Marc Pollefeys UNC Chapel Hill, some of the figures and slides are adapted from M. Pollefeys, J.S. Franco, J. Matusik s presentations,

More information

Fast Lighting Independent Background Subtraction

Fast Lighting Independent Background Subtraction Fast Lighting Independent Background Subtraction Yuri Ivanov Aaron Bobick John Liu [yivanov bobick johnliu]@media.mit.edu MIT Media Laboratory February 2, 2001 Abstract This paper describes a new method

More information

Volumetric Scene Reconstruction from Multiple Views

Volumetric Scene Reconstruction from Multiple Views Volumetric Scene Reconstruction from Multiple Views Chuck Dyer University of Wisconsin dyer@cs cs.wisc.edu www.cs cs.wisc.edu/~dyer Image-Based Scene Reconstruction Goal Automatic construction of photo-realistic

More information

Shape from Silhouettes I CV book Szelisky

Shape from Silhouettes I CV book Szelisky Shape from Silhouettes I CV book Szelisky 11.6.2 Guido Gerig CS 6320, Spring 2012 (slides modified from Marc Pollefeys UNC Chapel Hill, some of the figures and slides are adapted from M. Pollefeys, J.S.

More information

Parallel Computation of Spherical Parameterizations for Mesh Analysis. Th. Athanasiadis and I. Fudos University of Ioannina, Greece

Parallel Computation of Spherical Parameterizations for Mesh Analysis. Th. Athanasiadis and I. Fudos University of Ioannina, Greece Parallel Computation of Spherical Parameterizations for Mesh Analysis Th. Athanasiadis and I. Fudos, Greece Introduction Mesh parameterization is a powerful geometry processing tool Applications Remeshing

More information

Lecture 8 Active stereo & Volumetric stereo

Lecture 8 Active stereo & Volumetric stereo Lecture 8 Active stereo & Volumetric stereo Active stereo Structured lighting Depth sensing Volumetric stereo: Space carving Shadow carving Voxel coloring Reading: [Szelisky] Chapter 11 Multi-view stereo

More information

Correspondence and Stereopsis. Original notes by W. Correa. Figures from [Forsyth & Ponce] and [Trucco & Verri]

Correspondence and Stereopsis. Original notes by W. Correa. Figures from [Forsyth & Ponce] and [Trucco & Verri] Correspondence and Stereopsis Original notes by W. Correa. Figures from [Forsyth & Ponce] and [Trucco & Verri] Introduction Disparity: Informally: difference between two pictures Allows us to gain a strong

More information

Computer Vision I - Image Matching and Image Formation

Computer Vision I - Image Matching and Image Formation Computer Vision I - Image Matching and Image Formation Carsten Rother 10/12/2014 Computer Vision I: Image Formation Process Computer Vision I: Image Formation Process 10/12/2014 2 Roadmap for next five

More information

Real-Time Video-Based Rendering from Multiple Cameras

Real-Time Video-Based Rendering from Multiple Cameras Real-Time Video-Based Rendering from Multiple Cameras Vincent Nozick Hideo Saito Graduate School of Science and Technology, Keio University, Japan E-mail: {nozick,saito}@ozawa.ics.keio.ac.jp Abstract In

More information

Image Precision Silhouette Edges

Image Precision Silhouette Edges Image Precision Silhouette Edges by Ramesh Raskar and Michael Cohen Presented at I3D 1999 Presented by Melanie Coggan Outline Motivation Previous Work Method Results Conclusions Outline Motivation Previous

More information

Midterm Examination CS 534: Computational Photography

Midterm Examination CS 534: Computational Photography Midterm Examination CS 534: Computational Photography November 3, 2016 NAME: Problem Score Max Score 1 6 2 8 3 9 4 12 5 4 6 13 7 7 8 6 9 9 10 6 11 14 12 6 Total 100 1 of 8 1. [6] (a) [3] What camera setting(s)

More information

Using temporal seeding to constrain the disparity search range in stereo matching

Using temporal seeding to constrain the disparity search range in stereo matching Using temporal seeding to constrain the disparity search range in stereo matching Thulani Ndhlovu Mobile Intelligent Autonomous Systems CSIR South Africa Email: tndhlovu@csir.co.za Fred Nicolls Department

More information

Neue Verfahren der Bildverarbeitung auch zur Erfassung von Schäden in Abwasserkanälen?

Neue Verfahren der Bildverarbeitung auch zur Erfassung von Schäden in Abwasserkanälen? Neue Verfahren der Bildverarbeitung auch zur Erfassung von Schäden in Abwasserkanälen? Fraunhofer HHI 13.07.2017 1 Fraunhofer-Gesellschaft Fraunhofer is Europe s largest organization for applied research.

More information

CS5670: Computer Vision

CS5670: Computer Vision CS5670: Computer Vision Noah Snavely, Zhengqi Li Stereo Single image stereogram, by Niklas Een Mark Twain at Pool Table", no date, UCR Museum of Photography Stereo Given two images from different viewpoints

More information

Depth. Common Classification Tasks. Example: AlexNet. Another Example: Inception. Another Example: Inception. Depth

Depth. Common Classification Tasks. Example: AlexNet. Another Example: Inception. Another Example: Inception. Depth Common Classification Tasks Recognition of individual objects/faces Analyze object-specific features (e.g., key points) Train with images from different viewing angles Recognition of object classes Analyze

More information

Prof. Trevor Darrell Lecture 18: Multiview and Photometric Stereo

Prof. Trevor Darrell Lecture 18: Multiview and Photometric Stereo C280, Computer Vision Prof. Trevor Darrell trevor@eecs.berkeley.edu Lecture 18: Multiview and Photometric Stereo Today Multiview stereo revisited Shape from large image collections Voxel Coloring Digital

More information