Manhattan-world Stereo Y. Furukawa, B. Curless, S. M. Seitz, and R. Szeliski 2009 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.

Slides:



Advertisements
Similar presentations
Multi-view Stereo via Volumetric Graph-cuts
Advertisements

Pose Estimation and Segmentation of People in 3D Movies Karteek Alahari, Guillaume Seguin, Josef Sivic, Ivan Laptev Inria, Ecole Normale Superieure ICCV.
Efficient High-Resolution Stereo Matching using Local Plane Sweeps Sudipta N. Sinha, Daniel Scharstein, Richard CVPR 2014 Yongho Shin.
Stereo Many slides adapted from Steve Seitz. Binocular stereo Given a calibrated binocular stereo pair, fuse it to produce a depth image Where does the.
Multi-View Stereo for Community Photo Collections
Lecture 8: Stereo.
Stereo.
A Robust Pedestrian Detection Approach Based on Shapelet Feature and Haar Detector Ensembles Wentao Yao, Zhidong Deng TSINGHUA SCIENCE AND TECHNOLOGY ISSNl.
Reconstructing Building Interiors from Images Yasutaka Furukawa Brian Curless Steven M. Seitz University of Washington, Seattle, USA Richard Szeliski Microsoft.
Reconstructing Building Interiors from Images Yasutaka Furukawa Brian Curless Steven M. Seitz University of Washington, Seattle, USA 2011/01/16 蔡禹婷.
Boundary matting for view synthesis Samuel W. Hasinoff Sing Bing Kang Richard Szeliski Computer Vision and Image Understanding 103 (2006) 22–32.
Segmentation Using Max Flow/Min Cut Graph Cuts Based on "An Experimental Comparison of Min-Cut/Max-Flow Algorithms for Energy Minimization in Vision.“
Last Time Pinhole camera model, projection
Multiple View Geometry : Computational Photography Alexei Efros, CMU, Fall 2005 © Martin Quinn …with a lot of slides stolen from Steve Seitz and.
Today: Image Segmentation Image Segmentation Techniques Snakes Scissors Graph Cuts Mean Shift Wednesday (2/28) Texture analysis and synthesis Multiple.
Multi-view stereo Many slides adapted from S. Seitz.
Stereo Binocular Stereo Calibration (finish up) Next Time Motivation
Stereopsis Mark Twain at Pool Table", no date, UCR Museum of Photography.
The plan for today Camera matrix
3D from multiple views : Rendering and Image Processing Alexei Efros …with a lot of slides stolen from Steve Seitz and Jianbo Shi.
Stereo and Structure from Motion
Stereo Computation using Iterative Graph-Cuts
Aleixo Cambeiro Barreiro 광주과학기술원 컴퓨터 비전 연구실
IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. 20, NO. 11, NOVEMBER 2011 Qian Zhang, King Ngi Ngan Department of Electronic Engineering, the Chinese university.
Announcements PS3 Due Thursday PS4 Available today, due 4/17. Quiz 2 4/24.
Stereo Guest Lecture by Li Zhang
Project 1 artifact winners Project 2 questions Project 2 extra signup slots –Can take a second slot if you’d like Announcements.
Midterm went out on Tuesday (due next Tuesday) Project 3 out today Announcements.
Lecture 25: Multi-view stereo, continued
Multiple View Geometry : Computational Photography Alexei Efros, CMU, Fall 2006 © Martin Quinn …with a lot of slides stolen from Steve Seitz and.
Accurate, Dense and Robust Multi-View Stereopsis Yasutaka Furukawa and Jean Ponce Presented by Rahul Garg and Ryan Kaminsky.
3-D Scene u u’u’ Study the mathematical relations between corresponding image points. “Corresponding” means originated from the same 3D point. Objective.
Automatic User Interaction Correction via Multi-label Graph-cuts Antonio Hernández-Vela, Carlos Primo and Sergio Escalera Workshop on Human Interaction.
Computer Vision Spring ,-685 Instructor: S. Narasimhan WH 5409 T-R 10:30am – 11:50am Lecture #15.
Epipolar Geometry and Stereo Vision Computer Vision CS 543 / ECE 549 University of Illinois Derek Hoiem 03/05/15 Many slides adapted from Lana Lazebnik,
Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’04) /04 $20.00 c 2004 IEEE 1 Li Hong.
Announcements Project 1 artifact winners Project 2 questions
Structure from images. Calibration Review: Pinhole Camera.
Final Exam Review CS485/685 Computer Vision Prof. Bebis.
Mutual Information-based Stereo Matching Combined with SIFT Descriptor in Log-chromaticity Color Space Yong Seok Heo, Kyoung Mu Lee, and Sang Uk Lee.
Brief Introduction to Geometry and Vision
KinectFusion : Real-Time Dense Surface Mapping and Tracking IEEE International Symposium on Mixed and Augmented Reality 2011 Science and Technology Proceedings.
A General Framework for Tracking Multiple People from a Moving Camera
Joint Depth Map and Color Consistency Estimation for Stereo Images with Different Illuminations and Cameras Yong Seok Heo, Kyoung Mu Lee and Sang Uk Lee.
Graph Cut Algorithms for Binocular Stereo with Occlusions
Graph Cut 韋弘 2010/2/22. Outline Background Graph cut Ford–Fulkerson algorithm Application Extended reading.
City University of Hong Kong 18 th Intl. Conf. Pattern Recognition Self-Validated and Spatially Coherent Clustering with NS-MRF and Graph Cuts Wei Feng.
Recap from Monday Image Warping – Coordinate transforms – Linear transforms expressed in matrix form – Inverse transforms useful when synthesizing images.
Object Stereo- Joint Stereo Matching and Object Segmentation Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on Michael Bleyer Vienna.
Stereo Readings Szeliski, Chapter 11 (through 11.5) Single image stereogram, by Niklas EenNiklas Een.
Stereo Many slides adapted from Steve Seitz.
Feature-Based Stereo Matching Using Graph Cuts Gorkem Saygili, Laurens van der Maaten, Emile A. Hendriks ASCI Conference 2011.
Stereo Many slides adapted from Steve Seitz. Binocular stereo Given a calibrated binocular stereo pair, fuse it to produce a depth image image 1image.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL. 26, NO. 9, SEPTEMBER 2004 Yuri Boykov, Member, IEEE Vladimir Kolmogorov, Member, IEEE.
Computer Vision, Robert Pless
A Region Based Stereo Matching Algorithm Using Cooperative Optimization Zeng-Fu Wang, Zhi-Gang Zheng University of Science and Technology of China Computer.
Computer Vision Stereo Vision. Bahadir K. Gunturk2 Pinhole Camera.
Bahadir K. Gunturk1 Phase Correlation Bahadir K. Gunturk2 Phase Correlation Take cross correlation Take inverse Fourier transform  Location of the impulse.
Lecture 19: Solving the Correspondence Problem with Graph Cuts CAP 5415 Fall 2006.
Solving for Stereo Correspondence Many slides drawn from Lana Lazebnik, UIUC.
Journal of Visual Communication and Image Representation
Silhouette Segmentation in Multiple Views Wonwoo Lee, Woontack Woo, and Edmond Boyer PAMI, VOL. 33, NO. 7, JULY 2011 Donguk Seo
Photoconsistency constraint C2 q C1 p l = 2 l = 3 Depth labels If this 3D point is visible in both cameras, pixels p and q should have similar intensities.
Project 2 artifacts—vote now!! Project 3 questions? Start thinking about final project ideas, partners Announcements.
Energy minimization Another global approach to improve quality of correspondences Assumption: disparities vary (mostly) smoothly Minimize energy function:
Introduction à la vision artificielle VIII Jean Ponce Web:
CSE 185 Introduction to Computer Vision Stereo 2.
Automatic User Interaction Correction via Multi-label Graph-cuts
Computer Vision Stereo Vision.
Stereo vision Many slides adapted from Steve Seitz.
Presentation transcript:

Manhattan-world Stereo Y. Furukawa, B. Curless, S. M. Seitz, and R. Szeliski 2009 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp – 1429, Dongwook Seo Jan. 10, 2015

Intelligent Systems Lab. Introduction Multi-view stereo (MVS) approach Using properties of architectural scenes Focusing on the problem of recovering depth maps Manhattan-world assumption Advantages of proposed approach (within the constrained space of Manhattan- world scenes) It is remarkably robust to lack of texture, and able to model flat painted walls. It produces remarkably clean, simple models as outputs. Steps of the proposed algorithm Identifying dominant orientations in the scene Recovering a depth map for each image by assigning one of the candidate planes to each pixel in the image 2

Intelligent Systems Lab. Reconstruction pipeline 3

Intelligent Systems Lab. Hypothesis planes Solve for per-pixel disparity or depth values Restrict the search space to a set of axis-aligned hypothesis planes Seek to assign one of these plane labels to each pixel in the image Identifying hypothesis planes MVS preprocessing Extracting dominant axes Generating hypothesis planes 4

Intelligent Systems Lab. MVS preprocessing (1/2) 5

Intelligent Systems Lab. MVS preprocessing (2/2) 6

Intelligent Systems Lab. Extracting dominant axes 7

Intelligent Systems Lab. Generating hypothesis planes 8

Intelligent Systems Lab. Reconstruction 9

Intelligent Systems Lab. Data term (1/5) 10

Intelligent Systems Lab. Data term (2/5) 11

Intelligent Systems Lab. Data term (3/5) 12

Intelligent Systems Lab. Data term (4/5) 13

Intelligent Systems Lab. Data term (5/5) 14

Intelligent Systems Lab. Smoothness term (1/5) 15

Intelligent Systems Lab. Smoothness term (2/5) 16

Intelligent Systems Lab. Smoothness term (3/5) Exploiting dominant lines Junction of two dominant planes in a Manhattan-world scene Line is aligned with one of the vanishing points. => Structural constraints on depth map 17 Input imageExtracted dominant lines

Intelligent Systems Lab. Smoothness term (4/5) 18

Intelligent Systems Lab. Smoothness term (5/5) 19

Intelligent Systems Lab. Experimental results (1/5) Five real datasets Camera parameters for each dataset Using publicly available structure-from-motion (SfM) software [18] 20

Intelligent Systems Lab. Experimental results (2/5) 21

Intelligent Systems Lab. Experimental results (3/5) 22

Intelligent Systems Lab. Experimental results (4/5) 23

Intelligent Systems Lab. Experimental results (5/5) 24

Intelligent Systems Lab. Conclusion The 3D reconstruction of architectural scenes based on Manhattan-world assumption Produce remarkably clean and simple models Perform well even in texture-poor areas of the scene Future work Merging depth maps into large scenes 25

Intelligent Systems Lab. References [4] Y. Boykov and V. Kolmogorov. An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision. PAMI, 26:1124–1137, [5] Y. Boykov, O. Veksler, and R. Zabih. Fast approximate energy minimization via graph cuts. PAMI, 23(11):1222– 1239, [7] D. Comaniciu and P. Meer. Mean shift: A robust approach toward feature space analysis. PAMI, 24(5):603–619, [13] V. Kolmogorov and R. Zabih. What energy functions can be minimized via graph cuts? PAMI, 26(2):147–159,