Unified Multi-Cue Depth Estimation from Light-Field Images: Correspondence, Defocus, Shading, and Specularity

Michael Tao

EECS Department
University of California, Berkeley
Technical Report No. UCB/EECS-2015-174
July 21, 2015

http://www2.eecs.berkeley.edu/Pubs/TechRpts/2015/EECS-2015-174.pdf

Light-field cameras have recently become available to the consumer market. An array of micro-lenses captures enough information that one can refocus images after acquisition, as well as shift one's viewpoint within the sub-apertures of the main lens, effectively obtaining multiple views. Thus, depth cues from defocus, correspondence, specularity, and shading are available simultaneously in a single capture. Previously, defocus could be achieved only through multiple image exposures focused at different depths; correspondence and specularity cues needed multiple exposures at different viewpoints or multiple cameras; and shading required very well controlled scenes and low-noise data. Moreover, all four cues could not easily be obtained together.

In this thesis, we will present a novel framework that decodes the light-field images from a consumer Lytro camera and uses the decoded image to compute dense depth estimation by obtaining the four depth cues: defocus, correspondence, specularity, and shading. By using both defocus and correspondence cues, depth estimation is more robust with consumer-grade noisy data than previous works. Shading cues from light-field data enable us to better regularize depth and estimate shape. By using specularity, we formulate a new depth measure that is robust against specularity, making our depth measure suitable for glossy scenes. By combining the cues into a high quality depth map, the results are suitable for a variety of complex computer vision applications.

Advisor: Jitendra Malik and Ravi Ramamoorthi


BibTeX citation:

@phdthesis{Tao:EECS-2015-174,
    Author = {Tao, Michael},
    Editor = {Ramamoorthi, Ravi and Malik, Jitendra and Efros, Alexei (Alyosha)},
    Title = {Unified Multi-Cue Depth Estimation from Light-Field Images: Correspondence, Defocus, Shading, and Specularity},
    School = {EECS Department, University of California, Berkeley},
    Year = {2015},
    Month = {Jul},
    URL = {http://www2.eecs.berkeley.edu/Pubs/TechRpts/2015/EECS-2015-174.html},
    Number = {UCB/EECS-2015-174},
    Abstract = {Light-field cameras have recently become available to the consumer market. An array of micro-lenses captures enough information that one can refocus images after acquisition, as well as shift one's viewpoint within the sub-apertures of the main lens, effectively obtaining multiple views. Thus, depth cues from defocus, correspondence, specularity, and shading are available simultaneously in a single capture. Previously, defocus could be  achieved only through multiple image exposures focused at different depths; correspondence and specularity cues needed multiple exposures at different  viewpoints or multiple cameras; and shading required very well controlled scenes and low-noise data. Moreover, all four cues could not easily be obtained together.

In this thesis, we will present a novel framework that decodes the light-field images from a consumer Lytro camera and uses the decoded image to compute dense depth estimation by obtaining the four depth cues: defocus, correspondence, specularity, and shading. By using both defocus and correspondence cues, depth estimation is more robust with consumer-grade noisy data than previous works. Shading cues from light-field data enable us to better regularize depth and estimate shape. By using specularity, we formulate a new depth measure that is robust against specularity, making our depth measure suitable for glossy scenes. By combining the cues into a high quality depth map, the results are suitable for a variety of complex computer vision applications.}
}

EndNote citation:

%0 Thesis
%A Tao, Michael
%E Ramamoorthi, Ravi
%E Malik, Jitendra
%E Efros, Alexei (Alyosha)
%T Unified Multi-Cue Depth Estimation from Light-Field Images: Correspondence, Defocus, Shading, and Specularity
%I EECS Department, University of California, Berkeley
%D 2015
%8 July 21
%@ UCB/EECS-2015-174
%U http://www2.eecs.berkeley.edu/Pubs/TechRpts/2015/EECS-2015-174.html
%F Tao:EECS-2015-174