Introduction To IBR Ying Wu. View Morphing Seitz & Dyer SIGGRAPH’96 Synthesize images in transition of two views based on two images No 3D shape is required.

Slides:



Advertisements
Similar presentations
The fundamental matrix F
Advertisements

Lecture 11: Two-view geometry
CSE473/573 – Stereo and Multiple View Geometry
Image and View Morphing [Beier and Neely ’92, Chen and Williams ’93, Seitz and Dyer ’96]
View Morphing by Steven M. SeitzCharles R. Dyer Irwin Chiu Hau Computer Science McGill University Winter 2004 Comp 767: Advanced Topics in Graphics: Image-Based.
13th UWA CSSE Research Conference, Yanchep, Western Australia, 20 th -21 st September Slide 1 of 13 Keeping Faces Straight View Morphing for Graphics.
Dr. Hassan Foroosh Dept. of Computer Science UCF
View Morphing (Seitz & Dyer, SIGGRAPH 96)
CSCE 641 Computer Graphics: Image Mosaicing Jinxiang Chai.
Single-view metrology
Computational Photography: Image Mosaicing Jinxiang Chai.
Epipolar geometry. (i)Correspondence geometry: Given an image point x in the first view, how does this constrain the position of the corresponding point.
Lecture 7: Image Alignment and Panoramas CS6670: Computer Vision Noah Snavely What’s inside your fridge?
CS485/685 Computer Vision Prof. George Bebis
Lecture 6: Image transformations and alignment CS6670: Computer Vision Noah Snavely.
COMP322/S2000/L221 Relationship between part, camera, and robot (cont’d) the inverse perspective transformation which is dependent on the focal length.
CSCE 641 Computer Graphics: Image Mosaicing Jinxiang Chai.
Lecture 20: Two-view geometry CS6670: Computer Vision Noah Snavely.
More Mosaic Madness : Computational Photography Alexei Efros, CMU, Fall 2005 © Jeffrey Martin (jeffrey-martin.com) with a lot of slides stolen from.
Lec 21: Fundamental Matrix
CSE473/573 – Stereo Correspondence
Visualization- Determining Depth From Stereo Saurav Basu BITS Pilani 2002.
Image warping/morphing Digital Video Special Effects Fall /10/17 with slides by Y.Y. Chuang,Richard Szeliski, Steve Seitz and Alexei Efros.
3-D Scene u u’u’ Study the mathematical relations between corresponding image points. “Corresponding” means originated from the same 3D point. Objective.
Automatic Camera Calibration
Computer vision: models, learning and inference
Lecture 12 Stereo Reconstruction II Lecture 12 Stereo Reconstruction II Mata kuliah: T Computer Vision Tahun: 2010.
Homogeneous Coordinates (Projective Space) Let be a point in Euclidean space Change to homogeneous coordinates: Defined up to scale: Can go back to non-homogeneous.
Course 12 Calibration. 1.Introduction In theoretic discussions, we have assumed: Camera is located at the origin of coordinate system of scene.
Geometric Operations and Morphing.
Geometric Models & Camera Calibration
Digital Image Processing CCS331
Epipolar geometry Epipolar Plane Baseline Epipoles Epipolar Lines
Shape from Stereo  Disparity between two images  Photogrammetry  Finding Corresponding Points Correlation based methods Feature based methods.
3D Sensing and Reconstruction Readings: Ch 12: , Ch 13: , Perspective Geometry Camera Model Stereo Triangulation 3D Reconstruction by.
CS654: Digital Image Analysis Lecture 8: Stereo Imaging.
Metrology 1.Perspective distortion. 2.Depth is lost.
Lec 22: Stereo CS4670 / 5670: Computer Vision Kavita Bala.
Lecture 03 15/11/2011 Shai Avidan הבהרה : החומר המחייב הוא החומר הנלמד בכיתה ולא זה המופיע / לא מופיע במצגת.
Introduction to Soft Copy Photogrammetry
Affine Structure from Motion
CS-498 Computer Vision Week 7, Day 2 Camera Parameters Intrinsic Calibration  Linear  Radial Distortion (Extrinsic Calibration?) 1.
Bahadir K. Gunturk1 Phase Correlation Bahadir K. Gunturk2 Phase Correlation Take cross correlation Take inverse Fourier transform  Location of the impulse.
112/5/ :54 Graphics II Image Based Rendering Session 11.
EECS 274 Computer Vision Affine Structure from Motion.
1 Chapter 2: Geometric Camera Models Objective: Formulate the geometrical relationships between image and scene measurements Scene: a 3-D function, g(x,y,z)
Feature Matching. Feature Space Outlier Rejection.
Computer vision: models, learning and inference M Ahad Multiple Cameras
Digital Image Processing Additional Material : Imaging Geometry 11 September 2006 Digital Image Processing Additional Material : Imaging Geometry 11 September.
CS559: Computer Graphics Lecture 9: 3D Transformation and Projection Li Zhang Spring 2010 Most slides borrowed from Yungyu ChuangYungyu Chuang.
Image-Based Rendering Geometry and light interaction may be difficult and expensive to model –Think of how hard radiosity is –Imagine the complexity of.
CS-321 Dr. Mark L. Hornick 1 Three-Dimensional Graphics Problem How can you effectively display 3-D information on a 2-D display?
Example: warping triangles Given two triangles: ABC and A’B’C’ in 2D (12 numbers) Need to find transform T to transfer all pixels from one to the other.
Lecture 14: Projection CS4670 / 5670: Computer Vision Noah Snavely “The School of Athens,” Raphael.
Image Warping 2D Geometric Transformations
Image warping/morphing Digital Visual Effects, Spring 2006 Yung-Yu Chuang 2005/3/15 with slides by Richard Szeliski, Steve Seitz and Alexei Efros.
55:148 Digital Image Processing Chapter 11 3D Vision, Geometry
Prof. Adriana Kovashka University of Pittsburgh October 3, 2016
Geometric Model of Camera
CS4670 / 5670: Computer Vision Kavita Bala Lecture 20: Panoramas.
CS4670 / 5670: Computer Vision Kavita Bala Lec 27: Stereo.
Homogeneous Coordinates (Projective Space)
Epipolar geometry.
Announcements Review on Thurs Project 4 Extra office hour: Friday 4-5
Credit: CS231a, Stanford, Silvio Savarese
Course 6 Stereo.
Stereo vision Many slides adapted from Steve Seitz.
Image Stitching Linda Shapiro ECE/CSE 576.
Image Morphing using mesh warp and feature based warp
Image Stitching Linda Shapiro ECE P 596.
Presentation transcript:

Introduction To IBR Ying Wu

View Morphing Seitz & Dyer SIGGRAPH’96 Synthesize images in transition of two views based on two images No 3D shape is required

The Task

Image Morphing A morph is determined from two images I 0 and I 1 and maps C 0 : I 0  I 1 and C 1 : I 1  I 0 A warp function W 0 and W 1 give the displacement of each point p 0  I 0 and p 1  I 1 as a function of s  [0; 1]. The in-between images I s are computed by warping the two original images and averaging the pixel colors of the warped images.

Problems for image morphing Linearly interpolating two perspective views of a clock (far left and far right) causes a geometric bending effect in the in-between images. The dashed line shows the linear path of one feature during the course of the transformation. This example is indicative of the types of distortions that can arise with image morphing techniques.

Notations

Assumptions Two images I 1 and I 2 of the same 3D objects Their projection matrices  1 and  2 Pixel correspondences of the two images

Morphing Parallel Views

Parallel views Suppose the camera is moved from the world origin to position (C x,C y,0) and the focal length changes from f 0 to f 1, we have If p 0  I 0 and p 1  I 1 be projections of P=[X,Y,Z,1] T

Shape preserving So, what about non-parallel views?

Image Reprojection The 3x3 matrix is a projective transformation that reprojects the image plane of onto that of The operation of reprojection is very powerful because it allows allows the gaze direction to be modified after a photograph is taken

Non-parallel views

Choose the world Let I0 and I1 be two perspective views with projection matrices and Choose the world coordinate system so that C 0 and C 1 lie on the world X-axis, i.e, Choose the Y axis to be in the direction of the cross product of the two image plane normals

Three-step algorithm

Discussion Can you see the relation of the prewarp step and the stereo rectification that we have learnt before?

Exceptions: Singular views In the parallel configuration, each camera’s optical center is out of the field of view of the other. A singular configuration arises when the optical center of camera B is in the field of view of camera A. Because prewarping does not change the field of view, singular views cannot be reprojected to form parallel views.

The procedure

Examples

More examples