Supplementary Material: Piecewise Planar and Compact Floorplan Reconstruction from Images
|
|
- Colin Bates
- 5 years ago
- Views:
Transcription
1 Supplementary Material: Piecewise Planar and Compact Floorplan Reconstruction from Images Ricardo Cabral Carnegie Mellon University Yasutaka Furukawa Washington University in St. Louis 1. Algorithm Details We provide details of several steps in our algorithm, which are not the contributions of the work and ommited in the main paper, but are necessary to reproduce the work Structure classification initialization As in Sect. 6 of the main paper, we use 3D points and free-space to initialize structure classification labels. From 3D points We first detect 3D points that are on the floor, ceiling or walls, based on their positions and normals. A 3D point is detected to be on the floor if the point is at the floor height and its normal is along the up direction, allowing an error of 0.3m and 15 degrees, respectively. Points on the ceiling are detected in the same way. A 3D point belongs to a wall if its height is between the floor and the ceiling, and the point normal is near horizontal, allowing an error of 15 degrees. Detected 3D points are projected onto visible panoramas. A superpixel is assigned a structure label if the number of projected points with the label is at least 5 and more than the numbers for the other labels. From core free-space A wall should not exist in the free-space. Given a panorama, which is usually in the middle of the core free-space region, if its surrounding core free-space region is large, the distance between the panorama and the closest wall must be at least that far. Therefore, given a panorama and a (2D) direction, which corresponds to an image column, the distance from the panorama to the first pixel that is outside the core-free space along the direction, gives a lower bound on the distance between the panorama and a wall. As in Sect. 6 of the main paper, this lower-bound yields a set of pixels that must belong to the floor or ceiling in the corresponding image column Dynamic programming construction In Section 5.4 of the main paper, dynamic programming is used to compute the optimal path with the specified number of edges in two phases: 1) between every pair of adjacent anchor points; and 2) for an entire floorplan. In both phases, dynamic programming construction is simple. In Dijkstra s algorithm, each node remembers the cost of the optimal path that has been found so far together with the previous node in that path. In the first phase of our algorithm, suppose we are interested in a shortest path that has at most β edges between consecutive anchor points. Each node remembers β different optimal paths with k(= 1, 2, β) edges from the source, again together with the previous node each. We simply scan the entire graph β times, with a simple modification in the recurrunce formula, then the sink node contains the costs of the β optimal paths that consist of k(= 1, 2, β) edges, where each exact path can be obtained by a standard back-tracking. In the second phase, the first anchor point stores optimal paths with k(= 1, 2, β) edges from the start. We also know the set of optimal paths from the first anchor point to the second one, and hence, can easily construct the optimal paths with k(= 1, 2, 2β} edges from the start to the second anchor point. This step is repeated through all the anchor points until the end by the dynamic programming, and can find optimal paths with different numbers of edges from the start to the end, forming an entire floorplan. 2. Complete results and evaluations We did not have enough space to provide comprehensive experimental results and evaluations in the main paper, which are included in this supplementary material together with those in the main paper for being self-contained. Please see the caption for the explanation of each figure. References [1] Y. Furukawa, B. Curless, S. M. Seitz, and R. Szeliski. Reconstructing building interiors from images. In ICCV, [2] D. C. Lee, M. Hebert, and T. Kanade. Geometric reasoning for single image structure recovery. In CVPR,
2 Italian Figure 1. Sample panorama images illustrating the challenges in our datasets.
3 Figure 2. The final texture mapped mesh model rendered from two different viewpoints for each dataset.
4 Italian Figure 3. Continued.
5 Italian Figure 4. Multi-view stereo reconstructions are incomplete and miss many major structures. Figure 5. The left two columns show the extracted line segments (color represents the corresponding vanishing direction) and the structure classification result based on the line feature [2]. The right three columns show our structure classification results after initialization by MVS points, after initialization by free-space information, and the final result.
6 MVS points Camera centers Start/end-line Core free-space Floorplan-path Anchor points Italian Wine Store Points from structure classification Figure 6. The floorplan reconstruction is based on two kinds of 3D evidence: Wall evidence from 3D points (first column) and free-space evidence from visible rays associated with 3D points (second column). Red, green and blue illustrates high, medium and low confidence, respectively. After identifying a region with high free-space evidence as core free-space (grey), a shortest path problem is formulated to reconstruct a floorplan that goes around it (third column). To overcome shrinkage bias, we solve the problem again but with additional anchor points as constraints (fourth column). Ground is obtained manually by clicking room corners in images for comparison (fifth column).
7 Italian Figure 7. Comparative evaluations against the 2D version of the Manhattan volumetric graph-cuts [1]. See the right column of Fig. 6 for our results. From left to right, smoothness penalties are scaled by a factor of four each time.
8 Italian Figure 8. Comparative evaluations against the 3D volumetric graph-cuts technique [1] (left) against our method (right) for each dataset.
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 informationRoom Reconstruction from a Single Spherical Image by Higher-order Energy Minimization
Room Reconstruction from a Single Spherical Image by Higher-order Energy Minimization Kosuke Fukano, Yoshihiko Mochizuki, Satoshi Iizuka, Edgar Simo-Serra, Akihiro Sugimoto, and Hiroshi Ishikawa Waseda
More informationSIMPLE ROOM SHAPE MODELING WITH SPARSE 3D POINT INFORMATION USING PHOTOGRAMMETRY AND APPLICATION SOFTWARE
SIMPLE ROOM SHAPE MODELING WITH SPARSE 3D POINT INFORMATION USING PHOTOGRAMMETRY AND APPLICATION SOFTWARE S. Hirose R&D Center, TOPCON CORPORATION, 75-1, Hasunuma-cho, Itabashi-ku, Tokyo, Japan Commission
More informationMulti-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 informationContexts and 3D Scenes
Contexts and 3D Scenes Computer Vision Jia-Bin Huang, Virginia Tech Many slides from D. Hoiem Administrative stuffs Final project presentation Nov 30 th 3:30 PM 4:45 PM Grading Three senior graders (30%)
More informationContexts and 3D Scenes
Contexts and 3D Scenes Computer Vision Jia-Bin Huang, Virginia Tech Many slides from D. Hoiem Administrative stuffs Final project presentation Dec 1 st 3:30 PM 4:45 PM Goodwin Hall Atrium Grading Three
More informationStructured Indoor Modeling
Structured Indoor Modeling Satoshi Ikehata Hang Yan Washington University in St. Louis Yasutaka Furukawa Abstract This paper presents a novel 3D modeling framework that reconstructs an indoor scene as
More informationStructured Indoor Modeling
Structured Indoor Modeling Satoshi Ikehata Hang Yan Washington University in St. Louis Yasutaka Furukawa Abstract This paper presents a novel 3D modeling framework that reconstructs an indoor scene as
More informationCS5670: Computer Vision
CS5670: Computer Vision Noah Snavely Multi-view stereo Announcements Project 3 ( Autostitch ) due Monday 4/17 by 11:59pm Recommended Reading Szeliski Chapter 11.6 Multi-View Stereo: A Tutorial Furukawa
More informationImage 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 informationAutomatic Photo Popup
Automatic Photo Popup Derek Hoiem Alexei A. Efros Martial Hebert Carnegie Mellon University What Is Automatic Photo Popup Introduction Creating 3D models from images is a complex process Time-consuming
More informationCombining Monocular Geometric Cues with Traditional Stereo Cues for Consumer Camera Stereo
000 001 002 003 004 005 006 007 008 009 010 011 012 013 014 015 016 017 018 019 020 021 022 023 024 025 026 027 028 029 030 031 032 033 034 035 036 037 038 039 040 041 042 043 044 Combining Monocular Geometric
More informationCS 558: Computer Vision 13 th Set of Notes
CS 558: Computer Vision 13 th Set of Notes Instructor: Philippos Mordohai Webpage: www.cs.stevens.edu/~mordohai E-mail: Philippos.Mordohai@stevens.edu Office: Lieb 215 Overview Context and Spatial Layout
More informationarxiv: v1 [cs.cv] 28 Sep 2018
Camera Pose Estimation from Sequence of Calibrated Images arxiv:1809.11066v1 [cs.cv] 28 Sep 2018 Jacek Komorowski 1 and Przemyslaw Rokita 2 1 Maria Curie-Sklodowska University, Institute of Computer Science,
More informationManhattan-world Stereo and Surface Reconstruction
Manhattan-world Stereo and Surface Reconstruction Kuan-Ting Yu CSAIL MIT Cambridge, USA peterkty@csail.mit.edu Abstract Depth estimation from 2D images has been extensively studied in the computer vision
More informationDense 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 information3D Spatial Layout Propagation in a Video Sequence
3D Spatial Layout Propagation in a Video Sequence Alejandro Rituerto 1, Roberto Manduchi 2, Ana C. Murillo 1 and J. J. Guerrero 1 arituerto@unizar.es, manduchi@soe.ucsc.edu, acm@unizar.es, and josechu.guerrero@unizar.es
More informationCS395T paper review. Indoor Segmentation and Support Inference from RGBD Images. Chao Jia Sep
CS395T paper review Indoor Segmentation and Support Inference from RGBD Images Chao Jia Sep 28 2012 Introduction What do we want -- Indoor scene parsing Segmentation and labeling Support relationships
More informationDense 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 informationDETECTION OF 3D POINTS ON MOVING OBJECTS FROM POINT CLOUD DATA FOR 3D MODELING OF OUTDOOR ENVIRONMENTS
DETECTION OF 3D POINTS ON MOVING OBJECTS FROM POINT CLOUD DATA FOR 3D MODELING OF OUTDOOR ENVIRONMENTS Tsunetake Kanatani,, Hideyuki Kume, Takafumi Taketomi, Tomokazu Sato and Naokazu Yokoya Hyogo Prefectural
More informationCS 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 informationCombining Monocular Geometric Cues with Traditional Stereo Cues for Consumer Camera Stereo
Combining Monocular Geometric Cues with Traditional Stereo Cues for Consumer Camera Stereo Adarsh Kowdle, Andrew Gallagher, and Tsuhan Chen Cornell University, Ithaca, NY, USA Abstract. This paper presents
More informationCS 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 informationStereo vision. Many slides adapted from Steve Seitz
Stereo vision Many slides adapted from Steve Seitz What is stereo vision? Generic problem formulation: given several images of the same object or scene, compute a representation of its 3D shape What is
More informationWhat 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 informationPublic Library, Stereoscopic Looking Room, Chicago, by Phillips, 1923
Public Library, Stereoscopic Looking Room, Chicago, by Phillips, 1923 Teesta suspension bridge-darjeeling, India Mark Twain at Pool Table", no date, UCR Museum of Photography Woman getting eye exam during
More informationPhoto Tourism: Exploring Photo Collections in 3D
Photo Tourism: Exploring Photo Collections in 3D SIGGRAPH 2006 Noah Snavely Steven M. Seitz University of Washington Richard Szeliski Microsoft Research 2006 2006 Noah Snavely Noah Snavely Reproduced with
More informationSupport surfaces prediction for indoor scene understanding
2013 IEEE International Conference on Computer Vision Support surfaces prediction for indoor scene understanding Anonymous ICCV submission Paper ID 1506 Abstract In this paper, we present an approach to
More informationBIL 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 informationEvaluation of Large Scale Scene Reconstruction
Evaluation of Large Scale Scene Reconstruction Paul Merrell, Philippos Mordohai, Jan-Michael Frahm, and Marc Pollefeys Department of Computer Science University of North Carolina, Chapel Hill, USA Abstract
More information3D 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 informationReconstructing Building Interiors from Images
Reconstructing Building Interiors from Images Yasutaka Furukawa, Brian Curless, Steven M. Seitz University of Washington, Seattle, USA {furukawa,curless,seitz}@cs.washington.edu Richard Szeliski Microsoft
More informationReal-Time Visibility-Based Fusion of Depth Maps
Real-Time Visibility-Based Fusion of Depth Maps Paul Merrell 1, Amir Akbarzadeh 2, Liang Wang 2, Philippos Mordohai 1, David Nistér 2 and Marc Pollefeys 1 1 Department of Computer Science 2 Center for
More informationParsing Indoor Scenes Using RGB-D Imagery
Robotics: Science and Systems 2012 Sydney, NSW, Australia, July 09-13, 2012 Parsing Indoor Scenes Using RGB-D Imagery Camillo J. Taylor and Anthony Cowley GRASP Laboratory University of Pennsylvania Philadelphia,
More informationVOLUMETRIC VIDEO // PLENOPTIC LIGHTFIELD // MULTI CAMERA METHODOLOGIES JORDAN HALSEY // VR PLAYHOUSE
VOLUMETRIC VIDEO // PLENOPTIC LIGHTFIELD // MULTI CAMERA METHODOLOGIES JORDAN HALSEY // VR PLAYHOUSE VOLUMETRIC VIDEO // PLENOPTIC LIGHTFIELD // MULTI CAMERA METHODOLOGIES Pro: Highly realistic seated
More informationMulti-View Stereo for Static and Dynamic Scenes
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.
More informationTextureless Layers CMU-RI-TR Qifa Ke, Simon Baker, and Takeo Kanade
Textureless Layers CMU-RI-TR-04-17 Qifa Ke, Simon Baker, and Takeo Kanade The Robotics Institute Carnegie Mellon University 5000 Forbes Avenue Pittsburgh, PA 15213 Abstract Layers are one of the most well
More informationarxiv: v1 [cs.cv] 1 Aug 2017
Dense Piecewise Planar RGB-D SLAM for Indoor Environments Phi-Hung Le and Jana Kosecka arxiv:1708.00514v1 [cs.cv] 1 Aug 2017 Abstract The paper exploits weak Manhattan constraints to parse the structure
More information3D Geometric Computer Vision. Martin Jagersand Univ. Alberta Edmonton, Alberta, Canada
3D Geometric Computer Vision Martin Jagersand Univ. Alberta Edmonton, Alberta, Canada Multi-view geometry Build 3D models from images Carry out manipulation tasks http://webdocs.cs.ualberta.ca/~vis/ibmr/
More informationPiecewise Planar and Non-Planar Stereo for Urban Scene Reconstruction
Piecewise Planar and Non-Planar Stereo for Urban Scene Reconstruction David Gallup 1, Jan-Michael Frahm 1, and Marc Pollefeys 2 Department of Computer Science 1 Department of Computer Science 2 The University
More informationProcessing 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 informationProf. 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 informationStatic Scene Reconstruction
GPU supported Real-Time Scene Reconstruction with a Single Camera Jan-Michael Frahm, 3D Computer Vision group, University of North Carolina at Chapel Hill Static Scene Reconstruction 1 Capture on campus
More informationPassive 3D Photography
SIGGRAPH 2000 Course on 3D Photography Passive 3D Photography Steve Seitz Carnegie Mellon University University of Washington http://www.cs cs.cmu.edu/~ /~seitz Visual Cues Shading Merle Norman Cosmetics,
More informationLecture 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 informationMultiple 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 informationRecognizing Apples by Piecing Together the Segmentation Puzzle
Recognizing Apples by Piecing Together the Segmentation Puzzle Kyle Wilshusen 1 and Stephen Nuske 2 Abstract This paper presents a system that can provide yield estimates in apple orchards. This is done
More informationSimple 3D Reconstruction of Single Indoor Image with Perspe
Simple 3D Reconstruction of Single Indoor Image with Perspective Cues Jingyuan Huang Bill Cowan University of Waterloo May 26, 2009 1 Introduction 2 Our Method 3 Results and Conclusions Problem Statement
More informationStereo: the graph cut method
Stereo: the graph cut method Last lecture we looked at a simple version of the Marr-Poggio algorithm for solving the binocular correspondence problem along epipolar lines in rectified images. The main
More informationLarge Scale 3D Reconstruction (50 mins) Yasutaka Washington University in St. Louis
Large Scale 3D Reconstruction (50 mins) Yasutaka Furukawa @ Washington University in St. Louis Outline 1. Large scale MVS for organized photos (Aerial photos) 2. Large scale MVS for unorganized photos
More informationSupplementary Material for A Locally Linear Regression Model for Boundary Preserving Regularization in Stereo Matching
Supplementary Material for A Locally Linear Regression Model for Boundary Preserving Regularization in Stereo Matching Shengqi Zhu 1, Li Zhang 1, and Hailin Jin 2 1 University of Wisconsin - Madison 2
More informationChaplin, 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 informationCOMP 558 lecture 22 Dec. 1, 2010
Binocular correspondence problem Last class we discussed how to remap the pixels of two images so that corresponding points are in the same row. This is done by computing the fundamental matrix, defining
More informationImage-Based Modeling and Rendering
Image-Based Modeling and Rendering Richard Szeliski Microsoft Research IPAM Graduate Summer School: Computer Vision July 26, 2013 How far have we come? Light Fields / Lumigraph - 1996 Richard Szeliski
More informationModeling, Combining, and Rendering Dynamic Real-World Events From Image Sequences
Modeling, Combining, and Rendering Dynamic Real-World Events From Image s Sundar Vedula, Peter Rander, Hideo Saito, and Takeo Kanade The Robotics Institute Carnegie Mellon University Abstract Virtualized
More information3D Surface Reconstruction from 2D Multiview Images using Voxel Mapping
74 3D Surface Reconstruction from 2D Multiview Images using Voxel Mapping 1 Tushar Jadhav, 2 Kulbir Singh, 3 Aditya Abhyankar 1 Research scholar, 2 Professor, 3 Dean 1 Department of Electronics & Telecommunication,Thapar
More informationDynamic visual understanding of the local environment for an indoor navigating robot
Dynamic visual understanding of the local environment for an indoor navigating robot Grace Tsai and Benjamin Kuipers Abstract We present a method for an embodied agent with vision sensor to create a concise
More informationEECS 442 Computer vision. Announcements
EECS 442 Computer vision Announcements Midterm released after class (at 5pm) You ll have 46 hours to solve it. it s take home; you can use your notes and the books no internet must work on it individually
More information3D Fusion of Infrared Images with Dense RGB Reconstruction from Multiple Views - with Application to Fire-fighting Robots
3D Fusion of Infrared Images with Dense RGB Reconstruction from Multiple Views - with Application to Fire-fighting Robots Yuncong Chen 1 and Will Warren 2 1 Department of Computer Science and Engineering,
More informationProcessing 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 informationIMAGE-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 informationWatertight Planar Surface Reconstruction of Voxel Data
Watertight Planar Surface Reconstruction of Voxel Data Eric Turner CS 284 Final Project Report December 13, 2012 1. Introduction There are many scenarios where a 3D shape is represented by a voxel occupancy
More informationAn Efficient Image Matching Method for Multi-View Stereo
An Efficient Image Matching Method for Multi-View Stereo Shuji Sakai 1, Koichi Ito 1, Takafumi Aoki 1, Tomohito Masuda 2, and Hiroki Unten 2 1 Graduate School of Information Sciences, Tohoku University,
More informationClustering in Registration of 3D Point Clouds
Sergey Arkhangelskiy 1 Ilya Muchnik 2 1 Google Moscow 2 Rutgers University, New Jersey, USA International Workshop Clusters, orders, trees: Methods and applications in honor of Professor Boris Mirkin December
More informationContext. CS 554 Computer Vision Pinar Duygulu Bilkent University. (Source:Antonio Torralba, James Hays)
Context CS 554 Computer Vision Pinar Duygulu Bilkent University (Source:Antonio Torralba, James Hays) A computer vision goal Recognize many different objects under many viewing conditions in unconstrained
More informationCS4495/6495 Introduction to Computer Vision. 3B-L3 Stereo correspondence
CS4495/6495 Introduction to Computer Vision 3B-L3 Stereo correspondence For now assume parallel image planes Assume parallel (co-planar) image planes Assume same focal lengths Assume epipolar lines are
More informationSparse Point Cloud Densification by Using Redundant Semantic Information
Sparse Point Cloud Densification by Using Redundant Semantic Information Michael Hödlmoser CVL, Vienna University of Technology ken@caa.tuwien.ac.at Branislav Micusik AIT Austrian Institute of Technology
More informationLecture 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 informationProject 3 code & artifact due Tuesday Final project proposals due noon Wed (by ) Readings Szeliski, Chapter 10 (through 10.5)
Announcements Project 3 code & artifact due Tuesday Final project proposals due noon Wed (by email) One-page writeup (from project web page), specifying:» Your team members» Project goals. Be specific.
More informationFinal project bits and pieces
Final project bits and pieces The project is expected to take four weeks of time for up to four people. At 12 hours per week per person that comes out to: ~192 hours of work for a four person team. Capstone:
More informationViewing and Ray Tracing. CS 4620 Lecture 4
Viewing and Ray Tracing CS 4620 Lecture 4 2014 Steve Marschner 1 Projection To render an image of a 3D scene, we project it onto a plane Most common projection type is perspective projection 2014 Steve
More informationSome books on linear algebra
Some books on linear algebra Finite Dimensional Vector Spaces, Paul R. Halmos, 1947 Linear Algebra, Serge Lang, 2004 Linear Algebra and its Applications, Gilbert Strang, 1988 Matrix Computation, Gene H.
More information3D Shape Modeling by Deformable Models. Ye Duan
3D Shape Modeling by Deformable Models Ye Duan Previous Work Shape Reconstruction from 3D data. Volumetric image datasets. Unorganized point clouds. Interactive Mesh Editing. Vertebral Dataset Vertebral
More informationViewing and Ray Tracing
Viewing and Ray Tracing CS 4620 Lecture 4 2018 Steve Marschner 1 Projection To render an image of a 3D scene, we project it onto a plane Most common projection type is perspective projection 2018 Steve
More informationAutomatic Alignment of Indoor and Outdoor Building Models using 3D Line Segments
Automatic Alignment of Indoor and Outdoor Building Models using 3D Line Segments Tobias Koch, Marco Körner Remote Sensing Technology Technical University of Munich {tobias.koch,marco.koerner}@tum.de Friedrich
More informationProcessing 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 informationIdentify parallel lines, skew lines and perpendicular lines.
Learning Objectives Identify parallel lines, skew lines and perpendicular lines. Parallel Lines and Planes Parallel lines are coplanar (they lie in the same plane) and never intersect. Below is an example
More informationStereo. Many slides adapted from Steve Seitz
Stereo Many slides adapted from Steve Seitz Binocular stereo Given a calibrated binocular stereo pair, fuse it to produce a depth image image 1 image 2 Dense depth map Binocular stereo Given a calibrated
More informationEE795: 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 informationLightcuts. Jeff Hui. Advanced Computer Graphics Rensselaer Polytechnic Institute
Lightcuts Jeff Hui Advanced Computer Graphics 2010 Rensselaer Polytechnic Institute Fig 1. Lightcuts version on the left and naïve ray tracer on the right. The lightcuts took 433,580,000 clock ticks and
More information3D Reconstruction Using an n-layer Heightmap
3D Reconstruction Using an n-layer Heightmap David Gallup 1, Marc Pollefeys 2, and Jan-Michael Frahm 1 1 Department of Computer Science, University of North Carolina {gallup,jmf}@cs.unc.edu 2 Department
More informationAcquisition 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 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 informationOther Reconstruction Techniques
Other Reconstruction Techniques Ruigang Yang CS 684 CS 684 Spring 2004 1 Taxonomy of Range Sensing From Brain Curless, SIGGRAPH 00 Lecture notes CS 684 Spring 2004 2 Taxonomy of Range Scanning (cont.)
More informationThree-Dimensional Object Detection and Layout Prediction using Clouds of Oriented Gradients
ThreeDimensional Object Detection and Layout Prediction using Clouds of Oriented Gradients Authors: Zhile Ren, Erik B. Sudderth Presented by: Shannon Kao, Max Wang October 19, 2016 Introduction Given an
More informationMarkov Networks in Computer Vision
Markov Networks in Computer Vision Sargur Srihari srihari@cedar.buffalo.edu 1 Markov Networks for Computer Vision Some applications: 1. Image segmentation 2. Removal of blur/noise 3. Stereo reconstruction
More informationMore Single View Geometry
More Single View Geometry with a lot of slides stolen from Steve Seitz Cyclops Odilon Redon 1904 15-463: Computational Photography Alexei Efros, CMU, Fall 2007 Final Projects Are coming up fast! Undergrads
More information3D 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 informationMarkov Networks in Computer Vision. Sargur Srihari
Markov Networks in Computer Vision Sargur srihari@cedar.buffalo.edu 1 Markov Networks for Computer Vision Important application area for MNs 1. Image segmentation 2. Removal of blur/noise 3. Stereo reconstruction
More informationModel-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 informationBumblebee2 Stereo Vision Camera
Bumblebee2 Stereo Vision Camera Description We use the Point Grey Bumblebee2 Stereo Vision Camera in this lab section. This stereo camera can capture 648 x 488 video at 48 FPS. 1) Microlenses 2) Status
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 informationLayered Scene Decomposition via the Occlusion-CRF Supplementary material
Layered Scene Decomposition via the Occlusion-CRF Supplementary material Chen Liu 1 Pushmeet Kohli 2 Yasutaka Furukawa 1 1 Washington University in St. Louis 2 Microsoft Research Redmond 1. Additional
More informationAS AUTOMAATIO- JA SYSTEEMITEKNIIKAN PROJEKTITYÖT CEILBOT FINAL REPORT
AS-0.3200 AUTOMAATIO- JA SYSTEEMITEKNIIKAN PROJEKTITYÖT CEILBOT FINAL REPORT Jaakko Hirvelä GENERAL The goal of the Ceilbot-project is to design a fully autonomous service robot moving in a roof instead
More informationCS 4758: Automated Semantic Mapping of Environment
CS 4758: Automated Semantic Mapping of Environment Dongsu Lee, ECE, M.Eng., dl624@cornell.edu Aperahama Parangi, CS, 2013, alp75@cornell.edu Abstract The purpose of this project is to program an Erratic
More informationMultiview 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 informationNinio, J. and Stevens, K. A. (2000) Variations on the Hermann grid: an extinction illusion. Perception, 29,
Ninio, J. and Stevens, K. A. (2000) Variations on the Hermann grid: an extinction illusion. Perception, 29, 1209-1217. CS 4495 Computer Vision A. Bobick Sparse to Dense Correspodence Building Rome in
More informationModeling a Fluted Column in Google SketchUp
Architectural columns in ancient Greece, Rome, and even China used flutes - vertical grooves cut along the outside of the cylinder. If you want to create a model of an ancient temple, or perhaps one of
More informationVolumetric 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 informationAUTOMATED 3D MODELING OF URBAN ENVIRONMENTS
AUTOMATED 3D MODELING OF URBAN ENVIRONMENTS Ioannis Stamos Department of Computer Science Hunter College, City University of New York 695 Park Avenue, New York NY 10065 istamos@hunter.cuny.edu http://www.cs.hunter.cuny.edu/
More information