Computational Cameras

Wednesday, 8 August
1:45 - 3:30 pm
Room 6AB
Session Chair/Discussant: Marc Levoy, Stanford University

Active Refocusing of Images and Videos

A system for refocusing images and videos of dynamic scenes using a single-view depth estimation method. This method is based on the defocus of a sparse set of projected dots.

Francesc Moreno-Noguer
CVLAB, Ecole Polytechnique Fédérale de Lausanne

Peter N. Belhumeur
Shree K. Nayar
Columbia University

Multi-Aperture Photography

This paper describes a camera that simultaneously captures multiple images of a scene taken with different aperture settings and demonstrates algorithms for extrapolating depth of field, synthetic refocusing, and other editing.

Paul Green
Massachusetts Institute of Technology

Wenyang Sun
Wojciech Matusik
Mitsubishi Electric Research Laboratories (MERL)

Frédo Durand
Massachusetts Institute of Technology, Computer Science and Artificial Intelligence Laboratory

Dappled Photography: Mask-Enhanced Cameras for Heterodyned Light Fields and Coded Aperture Refocusing

This method exploits Fourier-domain remapping of 4D ray-space to capture 4D light fields on a 2D sensor in a conventional camera using a transmissive mask. No lens array is used.

Ashok Veeraraghavan
Ramesh Raskar
Amit Agrawal
Ankit Mohan
Mitsubishi Electric Research Laboratories (MERL)

Jack Tumblin
Northwestern University

Image and Depth From a Conventional Camera With a Coded Aperture

A simple modification to a conventional camera that allows for simultaneous recovery of both high-resolution image information and depth information from a single image.

Anat Levin
Rob Fergus
Frédo Durand
William T. Freeman
Massachusetts Institute of Technology, Computer Science and Artificial Intelligence Laboratory