Computational Photography and Videography

1. Computational Photography and Videography Christian Theobalt and Ivo Ihrke Winter term 09/10

2. Coordinates • MPI – room 019 • Wednesdays, 14:00 c.t. • Christian Theobalt • MPI, room 228 • theobalt@mpii.de • Ivo Ihrke • MPI, room 225 • ihrke@mpii.de • Mailing List • seminar-cpav09@mpi-inf.mpg.de • Web Page • http://www.mpi-inf.mpg.de/~theobalt/courses/Seminar_WS_2009/

3. Formal Requirements • Presence required • Read all papers and participate in discussion • One paper is “your paper” and you have to give a 40-45 minute presentation on it • Prepare a written report on the topic you presented • Grade: talk 50 %, report 50 %

4. Organizational Issues • Register by sending an Email to both of us • Topic assignment • Send list of ordered preferences by Friday (23rd of Oct.) • We try to accommodate wishes as well as possible • We send out assignment on Monday, 26th of Oct. • First topic presentation 2009/11/18 • (10 students)

5. Benefits • Practice one of the most important skills in science • Read and understand papers • Present scientific results • Discussion is essential • If you don’t participate you miss a big chance • Most ideas are developed in discussions about other papers • Prepare the seminar classes ! • Benefit from the interaction in the group !

6. Organizational Issues • Topics will be covered in the order appearing on the seminar web page • If necessary, and mutually agreed on, dates can be exchanged • Presentations • 45 min. • presenter leads the discussion on the papers • All participants are supposed to read the papers • Active participation in discussion is expected

7. Organizational Issues • Two scheduled meetings per topic • 1. 3 weeks prior to presentation • Read papers for this meeting • Ask questions if you have difficulties • Discuss plans for presentation • 2. 1 week prior to presentation • prepare a preliminary presentation • We can provide feedback

8. Organizational Issues • one office hour per week • Announced on seminar web page • You can ask questions by e-mail any time

9. Organizational Issues • Report • 6 – 8 pages summary of major ideas of your topic • 2 - 3 pages with your own ideas, e.g., • Discuss limitations not mentioned in the paper and sketch a solution • Try to suggest improvements • Novel ideas based on content described in the papers • Your ideas can be the result of the discussion after your presentation ! • The idea is that you get a feeling for your specific topic surpassing the level of simply understanding a paper.

10. Organizational Issues • Report • Due date 2010/02/19 (2 1/2 weeks after last seminar) • Pdf by e-mail • We provide a LaTeX-style on the seminar page • If you use other software make it look like the LaTeX-example

11. Adelson & Bergen: The plenoptic function and elements of early vision, Computational Models of Visual Processing 1991 Levoy & Hanrahan: Light Field Rendering, SIGGRAPH’96 Image-Based Rendering Concepts

12. Camera Models and Noise • Healy & Kondepudy: Radiometric CCD Calibration and Noise Estimation, PAMI 1994 • Kolb et al.: A Realistic Camera Model for Computer Graphics, SIGGRAPH 1995

13. Geometric Camera Calibration • Zhang: A flexible new technique for camera calibration, PAMI 2000 • Hartley & Zisserman, Multiple View Geometry in Computer Vision, chapter 5, Cambridge University Press, 2000

14. Fourier Analysis of Light Fields • Isaksen et al.: Dynamically Reparameterized Light Fields, SIGGRAPH 2000 • Ng: Fourier Slice Photography, SIGGRAPH 2005

15. Light Field Capture with Non-Refractive Modulators • Veeraraghavan et al: Dappled Photography: Mask-Enhanced Cameras for Heterodyned Light Fields and Coded Aperture Refocusing, SIGGRAPH 2007 • Lanman et al: Shield Fields: Modeling and Capturing 3D Occluders, SIGGRAPH Asia 2008

16. Multi-View Basics • Laurentini: The Visual Hull Concept for Silhouette-Based Image Understanding, PAMI 1994 • Matusik et al.: Image-Based Visual Hulls, SIGGRAPH 2000

17. Multi-view Stereo for Static and Dynamic Scenes • Furukawa et al., Accurate, Dense, and Robust Multi-view Stereopsis , CVPR 2007 • Zitnick et al., High-Quality Video View Interpolation Using a Layered Representation, SIGGRAPH 2004

18. Marker-less Motion Capture • Bregler et al., tracking people with twists and exponential maps, CVPR 1998 • Balan et al., detailed human shape and pose from images

19. Marker-less Performance Capture • Vlasic et al., Articulated Mesh Animation from Multi-view Silhouettes, SIGGRAPH 2008 • De Aguiar et al., Performance Capture from Sparse Multi-view Video, SIGGRAPH 2008

20. Video Recinematography • Gleicher et al., Re-Cinematography: Improving the Camerawork of Casual Video, ACM TOMCCAP • Feng Liu et al., Content-Preserving Warps for 3D Video Stabilization, SIGGRAPH 2009

21. Reconstruction from Community Photo Collections • Snavely et al., Photo Tourism: Exploring image collections in 3D, SIGGRAPH 2006 • Goesele et al., Multi-View Stereo for Community Photo Collections, ICCV 2008

22. Reconstruction with Time-of-Flight Cameras • Fusion of Time-of-Flight Depth and Stereo for High Accuracy Depth Maps (PDF), Jiejie Zhu, Liang Wang, Ruigang Yang and James Davis, CVPR 2008 • Hebert et al., 3d measurements from imaging laser radars: How good are they?, IVC 1992