Discontinuity Preserving Stereo with Small Baseline Multi-Flash Illumination Rogerio Feris 1, Ramesh Raskar 2, Longbin Chen 1, Karhan Tan 3 and Matthew.

Slides:



Advertisements
Similar presentations
5 x4. 10 x2 9 x3 10 x9 10 x4 10 x8 9 x2 9 x4.
Advertisements

QR Code Recognition Based On Image Processing
Efficient High-Resolution Stereo Matching using Local Plane Sweeps Sudipta N. Sinha, Daniel Scharstein, Richard CVPR 2014 Yongho Shin.
Public Library, Stereoscopic Looking Room, Chicago, by Phillips, 1923.
Gratuitous Picture US Naval Artillery Rangefinder from World War I (1918)!!
Real-Time Accurate Stereo Matching using Modified Two-Pass Aggregation and Winner- Take-All Guided Dynamic Programming Xuefeng Chang, Zhong Zhou, Yingjie.
Lecture 8: Stereo.
December 5, 2013Computer Vision Lecture 20: Hidden Markov Models/Depth 1 Stereo Vision Due to the limited resolution of images, increasing the baseline.
Last Time Pinhole camera model, projection
Stanford CS223B Computer Vision, Winter 2005 Lecture 6: Stereo 2 Sebastian Thrun, Stanford Rick Szeliski, Microsoft Hendrik Dahlkamp and Dan Morris, Stanford.
CS6670: Computer Vision Noah Snavely Lecture 17: Stereo
Multiple View Geometry : Computational Photography Alexei Efros, CMU, Fall 2005 © Martin Quinn …with a lot of slides stolen from Steve Seitz and.
Contents Description of the big picture Theoretical background on this work The Algorithm Examples.
© 2004 by Davi GeigerComputer Vision April 2004 L1.1 Binocular Stereo Left Image Right Image.
Computer Vision : CISC 4/689 Adaptation from: Prof. James M. Rehg, G.Tech.
Stanford CS223B Computer Vision, Winter 2006 Lecture 6 Stereo II Professor Sebastian Thrun CAs: Dan Maynes-Aminzade, Mitul Saha, Greg Corrado Stereo.
Introduction to Computer Vision 3D Vision Topic 9 Stereo Vision (I) CMPSCI 591A/691A CMPSCI 570/670.
Stereopsis Mark Twain at Pool Table", no date, UCR Museum of Photography.
The plan for today Camera matrix
CS 223b 1 More on stereo and correspondence. CS 223b 2 =?f g Mostpopular For each window, match to closest window on epipolar line in other image. (slides.
3D from multiple views : Rendering and Image Processing Alexei Efros …with a lot of slides stolen from Steve Seitz and Jianbo Shi.
Stockman MSU Fall Computing Motion from Images Chapter 9 of S&S plus otherwork.
Stereo Computation using Iterative Graph-Cuts
CSE473/573 – Stereo Correspondence
Announcements PS3 Due Thursday PS4 Available today, due 4/17. Quiz 2 4/24.
Multiple View Geometry : Computational Photography Alexei Efros, CMU, Fall 2006 © Martin Quinn …with a lot of slides stolen from Steve Seitz and.
Stereo matching Class 10 Read Chapter 7 Tsukuba dataset.
3-D Scene u u’u’ Study the mathematical relations between corresponding image points. “Corresponding” means originated from the same 3D point. Objective.
3D Scene Models Object recognition and scene understanding Krista Ehinger.
Computer Vision Spring ,-685 Instructor: S. Narasimhan WH 5409 T-R 10:30am – 11:50am Lecture #15.
Stereo Readings Trucco & Verri, Chapter 7 –Read through 7.1, 7.2.1, 7.2.2, 7.3.1, 7.3.2, and 7.4, –The rest is optional. Single image stereogram,
Northeastern University, Fall 2005 CSG242: Computational Photography Ramesh Raskar Mitsubishi Electric Research Labs Northeastern University Oct 19th,
Last Week Recognized the fact that the 2D image is a representation of a 3D scene thus contains a consistent interpretation –Labeled edges –Labeled vertices.
Lecture 12 Stereo Reconstruction II Lecture 12 Stereo Reconstruction II Mata kuliah: T Computer Vision Tahun: 2010.
Automatic Registration of Color Images to 3D Geometry Computer Graphics International 2009 Yunzhen Li and Kok-Lim Low School of Computing National University.
Rohith MV, Gowri Somanath, Chandra Kambhamettu Video/Image Modeling and Synthesis(VIMS) Lab, Dept. of Computer and Information Sciences Cathleen Geiger.
Object Stereo- Joint Stereo Matching and Object Segmentation Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on Michael Bleyer Vienna.
December 4, 2014Computer Vision Lecture 22: Depth 1 Stereo Vision Comparing the similar triangles PMC l and p l LC l, we get: Similarly, for PNC r and.
Geometry 3: Stereo Reconstruction Introduction to Computer Vision Ronen Basri Weizmann Institute of Science.
#MOTION ESTIMATION AND OCCLUSION DETECTION #BLURRED VIDEO WITH LAYERS
Depth Edge Detection with Multi- Flash Imaging Gabriela Martínez Final Project – Processamento de Imagem IMPA.
Structured Light Based Depth Edge Detection for Object Shape Recovery Cheolhwon Kim, Jiyoung Park, Juneho Yi School of Information and Communication Engineering.
Why is computer vision difficult?
Computer Vision, Robert Pless
Lec 22: Stereo CS4670 / 5670: Computer Vision Kavita Bala.
Computer Vision Stereo Vision. Bahadir K. Gunturk2 Pinhole Camera.
Computer Vision Lecture #10 Hossam Abdelmunim 1 & Aly A. Farag 2 1 Computer & Systems Engineering Department, Ain Shams University, Cairo, Egypt 2 Electerical.
CSE 185 Introduction to Computer Vision Stereo. Taken at the same time or sequential in time stereo vision structure from motion optical flow Multiple.
Bahadir K. Gunturk1 Phase Correlation Bahadir K. Gunturk2 Phase Correlation Take cross correlation Take inverse Fourier transform  Location of the impulse.
stereo Outline : Remind class of 3d geometry Introduction
Solving for Stereo Correspondence Many slides drawn from Lana Lazebnik, UIUC.
55:148 Digital Image Processing Chapter 11 3D Vision, Geometry Topics: Basics of projective geometry Points and hyperplanes in projective space Homography.
Jeong Kanghun CRV (Computer & Robot Vision) Lab..
Project 2 due today Project 3 out today Announcements TexPoint fonts used in EMF. Read the TexPoint manual before you delete this box.: AAAAA.
John Morris Stereo Vision (continued) Iolanthe returns to the Waitemata Harbour.
Speaker Min-Koo Kang March 26, 2013 Depth Enhancement Technique by Sensor Fusion: MRF-based approach.
Energy minimization Another global approach to improve quality of correspondences Assumption: disparities vary (mostly) smoothly Minimize energy function:
A Plane-Based Approach to Mondrian Stereo Matching
CS4670 / 5670: Computer Vision Kavita Bala Lec 27: Stereo.
Rogerio Feris 1, Ramesh Raskar 2, Matthew Turk 1
Image Processing and Reconstructions Tools
Fast Preprocessing for Robust Face Sketch Synthesis
Approximate Models for Fast and Accurate Epipolar Geometry Estimation
Geometry 3: Stereo Reconstruction
EECS 274 Computer Vision Stereopsis.
Computer Vision Stereo Vision.
Chapter 11: Stereopsis Stereopsis: Fusing the pictures taken by two cameras and exploiting the difference (or disparity) between them to obtain the depth.
Filtering An image as a function Digital vs. continuous images
Occlusion and smoothness probabilities in 3D cluttered scenes
Stereo vision Many slides adapted from Steve Seitz.
Presentation transcript:

Discontinuity Preserving Stereo with Small Baseline Multi-Flash Illumination Rogerio Feris 1, Ramesh Raskar 2, Longbin Chen 1, Karhan Tan 3 and Matthew Turk 1 1 University of California, Santa Barbara 2 Mitsubishi Electric Research Labs 3 Epson Palo Alto Lab

Introduction Correspondence Problem Stereo Near Depth Discontinuities: - Occlusion Problem - Perspective Distortions - Violation of Smoothness Constraints Passive Versus Active Methods

Introduction Our Approach: Small Baseline Multi-Flash Illumination - Simple, Inexpensive - Compact, Self-Contained - Discontinuity Preserving

Depth Edges with Multi-Flash Raskar, Tan, Feris, Yu, Turk – ACM SIGGRAPH 2004

Bottom Flash Top Flash Left Flash Right Flash Ratio images and directions of epipolar traversal Shadow-Free Depth Edges Shadow-FreeDepth Edges

Qualitative Depth Map

Qualitative Depth Sign of Depth Edge - Indicates which side is the foreground and which side is the background Shadow Width - Encodes object relative distances

Sign of Depth Edge (+) Foreground (-) Background Original Ratio Left Ratio Right Signed Edges

Shadow Width Bottom Flash Image Ratio Image Plot Along Scanline

Shadow Width Bottom Flash Image Ratio Image Shadow Width Estimation: Meanshift Segmentation algorithm applied on the ratio image

Imaging Geometry Object Flash Shadow Camera B z1z1 z2z2 f Shadow Width d

Qualitative Depth Working on this Equation … Log Depth Difference Shadow Width Gradient-Domain Problem!

Qualitative Depth 1) Compute Sharp Depth Gradient G = (G h,G v ) Log Depth Difference Sign of depth edge 2) Compute Q by integrating G (Poisson Equation) 3) Qualitative depth map Q = exp(Q)

Qualitative Depth Useful Prior Information for Stereo !

Occlusion Map

Partial Occlusion Problem Object Camera Occlusion AB (Seen by A but not by B)

Occlusion Bounded by Shadows Object CameraAB Flash Occlusion (Seen by A but not by B)

Occlusion Bounded by Shadows Object CameraAB Flash Lower Bound Shadow

Occlusion Bounded by Shadows Object CameraAB Flash Upper Bound Shadow

Occlusion Bounded by Shadows Object Camera Occlusion AB Average of Upper/Lower Shadow widths Flash

Occlusion Bounded by Shadows Occlusion Map Left ViewRight View

Discontinuity Preserving Stereo Matching

Local Stereo Problem: Shape and size of correlation window - Small Window Ambiguities / Noise - Large Window Problems at Depth Discontinuities Depth Edge Preserving Local Stereo

Local Stereo Smooth Disparity Delimited by depth edges + Occlusions Correlation Window Problem: Shape and size of correlation window - Small Window Ambiguities / Noise - Large Window Problems at Depth Discontinuities Depth Edge Preserving Local Stereo

Local Stereo Left View Depth Edges + OcclusionGround Truth Challenging Scene: - Ambiguous patterns, textureless regions, geometrically complex object, thin structures

Local Stereo Conventional 9x9 Conventional 31x31 Our Approach 31x Conventional Stereo Our Approach

Global Stereo Global Optimization – Markov Random Field (MAP-MRF) X = {x s } Disparity of each pixel (Hidden) Y = {y s } Matching cost at each disparity (Observed) X3X3 X1X1 X2X2 X7X7 X4X4 X6X6 X5X5 X8X8 y1y1 y2y2

Global Stereo Global Optimization – Markov Random Field (MAP-MRF) X = {x s } Disparity of each pixel (Hidden) Y = {y s } Matching cost at each disparity (Observed) Data Term Smoothness Term Inference by Belief Propagation [Jian Sun et al, 2003]

Global Stereo Qualitative Depth Map as Evidence - Used to set the smoothness term - Information propagation is stopped at depth edges - Encourage disparities for neighboring pixels according to depth difference in qualitative map Occlusion Penalty

Global Stereo Conventional Belief Propagation Our Approach RMS: RMS:

Conclusions Contributions - Stereo with small baseline illumination - Useful Feature Maps (Qualitative Depth + Occlusion Map) - Enhanced Local and Global Stereo Algorithms Pros / Cons - Robust, Simple, Inexpensive and Compact - Limited to handle outdoor scenes and motion Website (datasets, source code) -

Thank you ! Multi-Flash Stereo Webpage Four Eyes Lab, UCSB

Occlusion Bounded by Shadows Occlusion Detection by averaging length of shadows Images taken with light sources surrounding the other camera