Computational Photography and Video

MIT CSAIL Computer Graphics Group


Digital photography has already dramatically changed the ease with which we take and share pictures. We strongly believe that digital photography will also bring a second revolution: The flexibility of digital processing has the potential to greatly improve the quality of pictures. The engineering of traditional cameras, lenses and films has reached impressive results, but has always been limited by the strong constraints of chemistry, optics and analog processes. This led master photographers to create a rich craft and to spend hours to finalize each print, relying on skills that are out of reach of most users. This is even more true for motion pictures, where the sheer number of frames makes the production of quality movies the privilege of a few professionals. With the advent of digital cameras, most of these constraints disappear and the processing possibilities are endless. Powerful image enhancement techniques inspired by physical and phenomenological computer graphics methods can be applied to the data of the sensor in order to generate more compelling pictures.

See the more general MIT Computational Photography and Video web page

Symposium on Computational Photography, at MIT (May 2005).



Frédo Durand,Soonmin Bae, Elmar Eisemann, Sara Su, Sylvain Paris, Jiawen "Kevin" Chen, Paul Green

Contact:; web:


Real-time Edge-Aware Image Processing with the Bilateral Grid
Jiawen Chen, Sylvain Paris, Frédo Durand
ACM Transactions on Graphics, 26(3), (Proc.Siggraph), July 2007
Multi-aperture Photography
Paul Green, Wenyang Sun, Wojciech Matusik, Frédo Durand.
ACM Transactions on Graphics, 26(3), (Proc.Siggraph), July 2007
Image and Depth from a Conventional Camera with a Coded Aperture
Anat Levin, Rob Fregus, Frédo Durand, William Freeman
ACM Transactions on Graphics, 26(3), (Proc.Siggraph), July 2007
A Topological Approach to Hierarchical Segmentation using Mean Shift
Sylvain Paris and Frédo Durand
Proceedings of the IEEE conference on Computer Vision and Pattern Recognition (CVPR'07)
Defocus Magnification
Soonmin Bae and Frédo Durand
Proceedings of Eurographics 2007

Two-scale Tone Management for Photographic Look.
Soonmin Bae, Sylvain Paris, and Frédo Durand.
ACM Transactions on Graphics (Proceedings of ACM SIGGRAPH'06)

A Fast Approximation of the Bilateral Filter using a Signal Processing Approach
Sylvain Paris and Frédo Durand
European Conference on Computer Vision (ECCV'06)
(Code provided!!)

Antialiasing for Automultiscopic Displays
M. Zwicker, W. Matusik, F. Durand, H. Pfister
Proceedings of Eurographics Symposium on Rendering, 2006.

Motion Magnification
Ce Liu, Antonio Torralba, William T. Freeman, Frédo Durand and Edward H. Adelson

Defocus Video Matting
Morgan McGuire, Wojciech Matusik, Hanspeter Pfister, John F. Hughes, and Frédo Durand

De-Emphasis of Distracting Image Regions Using Texture Power Maps
Sara L. Su, Frédo Durand, and Maneesh Agrawala
Proc. of Texture 2005, Beijing, China, October 2005.
Flash Photography Enhancement Via Intrinsic Relighting
Elmar Eisemann and Frédo Durand
Fast Bilateral Filtering for the Display of High-Dynamic-Range Images
Frédo Durand and Julie Dorsey
An Invitation to Discuss Computer Depiction
Frédo Durand
ACM/Eurographics Symp. NPAR'02.
Image-Based Modeling and Photo Editing
Byong Mok Oh, Max Chen, Julie Dorsey and Frédo Durand
in the Proceedings of Siggraph'2001.
Decoupling Strokes and High-Level Attributes for Interactive Traditional Drawing
Frédo Durand, Victor Ostromoukhov, Mathieu Miller, François Duranleau, and Julie Dorsey
in the Proceedings of the 12th Eurographics Workshop on Rendering, June 2001.

Related courses


6.088 Digital and Computational Photography
6.882 Advanced Computational Photography

(The above link does not have all ppt files. See here for the missing one.)
see also 2006 offering with Bill Freeman


6.A44 Computational Photography

Freshman seminar

A Gentle Introduction to Bilateral Filtering and its Applications

SIGGRAPH 2007 Course, together with Sylvain Paris, Pierre Kornprobst, and Jack Tumblin.
Monday morning (8:30am - 12:15pm)

The Art and Science of Depiction (Spring 2001)

This class explores perceptual and technical aspect of pictures, and more precisely the depiction of reality on a 2D medium. The focus is on an in-breadth multidisciplinary approach. Here are the slides of a talk I gave at the University College of London to outline the class. And here is a more recent version given at Stanford (1 slide per page or 6 slides per page)


Perceptual and Artistic Principles for Effective Computer Depiction

SIGGRAPH 2002 Course, together with Maneesh Agrawala, Bruce Gooch, Victoria Interrante, Victor Ostromoukhov and Denis Zorin.