1. Computational Photography Prof. Feng Liu Spring 2015 http://www.cs.pdx.edu/~fliu/courses/cs510/ 03/30/2015

2. Today  Course overview Admin. Info Computational Photography 2

3. People  Lecturer: Prof. Feng Liu Room FAB 120-09 Office Hours: MW 3:30-4:30pm fliu@cs.pdx.edu 3

4. Web and Computer Account  Course website http://www.cs.pdx.edu/~fliu/courses/cs510/ Class mailing list  https://groups.google.com/forum/#!forum/cs510-computational- photography-2015  Everyone needs a Computer Science department computer account Get account at CAT http://cat.pdx.edu 4

5. Textbooks & Readings  Computer Vision: Algorithms and Applications Computer Vision: Algorithms and Applications By R. Szeliski Available online, free  Learning OpenCV: Computer Vision with the OpenCV Library Learning OpenCV: Computer Vision with the OpenCV Library By Gary Bradski and Adrian Kaehler  Papers recommended by the lecturers 5

6. Grading  40%: Readings  60%: Project 6

7. Readings  About 2 papers every week Write a brief summary for one of the papers  Totally less than 500 words 1.What problem is addressed? 2.How it is solved? 3.The advantages of the presented method? 4.The limitations of the presented method? 5. How to improve this method? 7

8. Project  Literature Study Option OK, not exciting… Read a rich set of literature on one topic And write a survey paper  System Option Good and popular Implement an easy-to-use system based on an existing algorithm  Research Option Excellent, less popular Define a new problem and solve it Or, develop a new solution to an existing problem 8

9. Project  Group options 1 or 2 members for the System and Research Options  Credits will evenly divided among group members Only 1 member for the Literature Study Option 9

10. Project Timeline  04/12: Project proposal due Submit a short project proposal 300 to 500 words  06/01-06/03: In-class project presentation Around 10-12 minutes  5pm, 06/05: Final report due Submit a report, test data set and source code Late submission policy  Your project will be accepted until 5pm, 06/07 But, will be penalized according to G=G0*(1-n*0.05/24), where n is the number of hours delayed, G0 is the raw score, and G is your final score. 10

11. Programming tools  C/C++ under Windows Preferable Visual Studio 2008 or 2010 Highly recommended You can use the OpenCV libraries Other graphics and vision libraries  Matlab Recommended  Others OK As long as it works for you 11

12. OpenCV  Open Source Computer Vision library http://opencv.willowgarage.com/wiki/ V 2.4.9 Perhaps the most popular toolkits for computer vision Provides APIs for a wide range of vision algorithms Highly recommended for your project 12

13. Lab Facilities  EB 325: Windows Lab Visual Studio 2012 installed  You need a Computer Science department account to use any CS labs Request one from CAT 13

14. Admin Questions? 14

15. Today  Course overview Admin. Info Computational Photography  Computational Photography 15

16. What Is Computational Photography  An extension of traditional (digital) photography that combines computational techniques from computer vision and computer graphics for improving image making Digital Photography and Optics Computer Vision Computer Graphics CP Slide credit: C. Dyer 16

17. Filter: De-noise 17 noisy image naïve denoising Gaussian blur better denoising edge-preserving filter Slide credit: Sylvain Paris and Frédo Durand

18. De-Blur 18 Original photograph Output Slide credit: Fergus et al.

19. Super-resolution 19 Reprint from Fattal 07

20. Super-resolution 20 Reprint from Liu et al. 2001

21. Color2Gray 21 Color Grayscale New Algorithm Slide credit: Gooch et al.

22. Tone Adjustment 22 Input Output Reprint from Lischinski et al. 06

23. Shadow Editing 23 Input Output

24. High Dynamic Range Imaging 24 Reprint from G. Brown 2006

25. Panorama 25 Reprint from Brown and Lowe 2007

26. Segmentation & Matting 26 Photos from: http://www.juew.org/projects/RobustMatting/index.html

27. Picturing Place: Building Rome in a Day 27 Photo from: http://grail.cs.washington.edu/rome/ Input Output

28. Picturing Place: Photo Tourism 28 Photo from: http://phototour.cs.washington.edu/

29. Stabilization http://web.cecs.pdx.edu/~fliu/project/3dstab.htm 29

30. Stereoscopic 3D 30 Image source: http://www.extremetech.com/extreme/128963-how-digital-technology-is-reinventing-cinema

31. Stereoscopic 3D 31

32. Stereoscopic 3D 32 Image source: http://www.digitalproductionme.com/article-4580-3d--bad-for-you/#.UI-QfGdTDK0

33. Computational Stereoscopic Cinematography 33

34. Computational Stereoscopic Cinematography 34

35. Next Time  Camera 35