PPT-2D transformations (a.k.a. warping)

16385 Computer Vision Spring 2019 Lecture 7 httpwwwcscmuedu16385 Course announcements Homework 2 is posted on the course website It is due on February 27 th at 2359 pm Start early because it is much larger and more difficult than homework 1. a 12 22 a a mn is an arbitrary matrix Rescaling The simplest types of linear transformations are rescaling maps Consider the map on corresponding to the matrix 2 0 0 3 That is 7 2 0 0 3 00 brPage 2br Shears The next simplest type of linear transfo Ch. 2 Lesson 3. Pg. 123. What will you will learn?. Enlarge Photographs. Make something from a pattern. Identify Similarity. Two figures are . similar. if the second can be obtained from the first by a sequence of transformations and dilations. Dongliang. . Zhang, . Xin. Wang, . Yunsong. Huang, Gerard Schuster. KAUST. Outline. . Conclusions. Motivation. Flatten the common image gathers. Numerical Example. Test . on . Marmousi. model and GOM data. / Morphing. Computational Photography. Connelly Barnes. [. Wolberg. 1996, Recent Advances in Image Morphing]. Some slides from . Fredo. Durand, Bill Freeman, James Hays. Morphing Video: Women in Art. Lecture 8: Warping, Morphing, 3D Transformation. Li Zhang. Spring 2010. Most slides borrowed from . Yungyu Chuang. Last time: Forward . warping. fwarp(I, I’, T). {. for (y=0; y<I.height; y++). WU PO-HUNG. Morphing. http://www.youtube.com/watch?v=wZurRt0TidI. Outline. Introduction. Warping. Forward Mapping. Inverse Mapping. Resample. Cross Dissolve. Mesh-Based Warping . Introduction. What is morphing. Presented by Tam Vu. Gayathri. . Chandrasekaran. *, . Tam Vu*, Alexander . Varshavsky. †. , . Marco . Gruteser. *. , Richard . P. . Martin. *. , . Jie. . Yang. ‡. , . Yingying. . Chen. ‡. *WINLAB. Transformations. CS5670: Computer Vision. Noah Snavely. Reading. Szeliski: Chapter 3.6. Image alignment. Why don’t these image line up exactly?. What is the geometric relationship between these two images?. Linda Shapiro. CSE 455 . 1. Combine two or more overlapping images to make one larger image. Add example. Slide credit: . Vaibhav Vaish. 2. How to do it?. Basic Procedure. Take a sequence of images from the same position. Linda Shapiro. EE/CSE 576. . 1. Combine two or more overlapping images to make one larger image. Add example. Slide credit: . Vaibhav Vaish. 2. How to do it?. Basic Procedure. Take a . sequence of images . Presented by Tam Vu. Gayathri. . Chandrasekaran. *, . Tam Vu*, Alexander . Varshavsky. †. , . Marco . Gruteser. *. , Richard . P. . Martin. *. , . Jie. . Yang. ‡. , . Yingying. . Chen. ‡. *WINLAB. Learning Targets: 8.G.2,8.G.3, 8.G.4. Follow the slides to learn more about transformations. Students should have paper and a pencil for notes at their desk while going through this presentation.. Transformation: a transformation is a change in position, shape or size.. CS5670: Computer Vision. Reading. Szeliski. : Chapter 3.6. Announcements. Project 2 out, due Thursday, March 3 by 8pm. Do be done in groups of 2 – if you need help finding a partner, try Ed Discussions or let us know. Ángel. Bautista. 1,2. , Laura Igual. 1,2. ,. Josep. Moya. 3. , . Verónica. Violant. 2. , . Oriol. Pujol. 1,2. and Sergio Escalera. 1,2. Computer Vision Center (CVC). 1. , University of Barcelona (UB).