tutorial 7
T7  Computational Photography

Date: Tuesday, September 4th, Time: 09:00 - 12:30, Location: Lecture Room 309

Organizers:  Ramesh Raskar (MERL)
Jack Tumblin (Northwestern University)
Speakers:  Ramesh Raskar (MERL)
Jack Tumblin (Northwestern University)


We describe the latest computational methods in digital imaging that overcome the traditional limitations of a camera and enable novel imaging applications. The tutorial provides a practical guide to topics in image capture and manipulation methods for generating compelling pictures for computer graphics and for extracting scene properties for computer vision, with several examples. There has always been an interest in the computer graphics community for image-based applications. But, thanks to the growing prevalence of digital cameras, there has recently been a renewed interest in digital photography-based research, tools and products. The papers at Eurographics and Siggraph conferences include high dynamic range, matting, image fusion, synthetic aperture using camera arrays, flash photography and cartooning. A more detailed list is included in the sample bibliography. We plan to give an overview of these publications, discuss the relevant computer vision algorithms, and explain the impact of topics in scientific imaging on photography.


Extended Summary

Computational photography combines plentiful computing, digital sensors, actuators, and lights to escape the limitations of traditional film cameras. Unbounded dynamic range, variable focus, resolution, and depth of field, hints about shape, reflectance, and lighting, and new interactive forms of photos that are partly snapshots and partly videos are just some of the new applications found in computational photography. Many computational photography ideas are new to digital artists and programmers, even if they are very familiar with film and digital photography techniques. This emerging multi-disciplinary field combines new and old ideas from both image capture and computational methods for images that may present a steep learning curve. For example, few photographers may know recent high dynamic range imaging methods, and image processing researchers face rapidly changing capture, alignment and noise issues in arrays of digital cameras. These topics, however, can be easily learned without extensive background. The goal of this tutorial is to present both aspects in a compact form. The tutorial briefly reviews fundamental topics in digital imaging and then provides a practical guide to underlying techniques beyond image processing such as gradient domain operations, graph cuts, bilateral filters and optimizations. Computational capture methods include sophisticated sensors, light sources, and on-board processing. Examples include adaptation to sensed scene depth and illumination, interactive pictures made by varying camera parameters or actively modifying the flash illumination parameters. Computational reconstruction methods include ?photomontage? that optimally fuses information from multiple images, improves signal to noise ratio and extracts scene features such as depth edges. The participants learn about topics in image capture and manipulation methods for generating compelling pictures for computer graphics and for extracting scene properties for computer vision, with several examples. We hope to provide enough fundamentals to satisfy the technical specialist without intimidating the curious graphics researchers interested in photography.

  1. Tutorial Introduction and Overview (5 min)
    Speaker: Ramesh Raskar

  2. Concepts in Computational Photography (20 min)
    Speaker: Jack Tumblin

  3. Understanding Film-like Photography (20 min)
    Speaker: Ramesh Raskar

  4. Improving Film-like Photography (20 min)
    Speaker: Jack Tumblin

  5. Image Processing Tools (20 min)
    Speaker: Jack Tumblin

  6. Break

  7. Image Reconstruction Techniques (15 min)
    Speaker: Jack Tumblin

  8. Computational Illumination (30 min)
    Speaker: Ramesh Raskar

  9. Future Cameras (35 min)
    Speaker: Ramesh Raskar

Speakers' Background

Ramesh Raskar is a Senior Research Scientist at MERL. He studies computational aspects of images and illumination. His work spans a range of topics in computational photography, projective emitters, non-photorealistic rendering and intelligent user interfaces. Current projects include optical heterodyning photography, flutter shutter camera, composite RFID (RFIG), multi-flash non-photorealistic camera for depth edge detection, locale-aware mobile projectors, image fusion for context enhancement and quadric transfer methods for multi-projector curved screen displays. Dr. Raskar received the TR100 Award, Technology Review's 100 Top Young Innovators Under 35 worldwide, 2004 and Global Indus Technovator Award 2003, instituted at MIT to recognize the top 20 Indian technology innovators on the globe. He holds 25 US patents and has received Mitsubishi Electric Invention Awards in 2003, 2004 and 2006.

Jack Tumblin is an Assistant Professor of Computer Science at Northwestern University. His interests include novel photographic sensors and lighting devices to assist museum curators in historical preservation, computer graphics and visual appearance, and image-based modeling and rendering. During his doctoral studies at Georgia Tech and post-doc at Cornell, he investigated tone-mapping methods to depict high-contrast scenes. His MS in Electrical Engineering (December 1990) and BSEE (1978), also from Georgia Tech, bracketed his work as co-founder of IVEX Corp., (>45 people as of 1990) where he designed flight simulators. He was co-organizer of Computational Photography courses at Siggraph 2005 and 2006. He was an Associate Editor of ACM Transactions on Graphics 2001-2006, and holds 9 patents.

« Back
Last update : 12.05.2011

If you have any comments regarding this webpage please contact EG07 staff.