Learning lightness from human judgement on relative reflectance
Authors:
- 1 June 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 2965-2973
Abstract
We develop a new approach to inferring lightness, the perceived reflectance of surfaces, from a single image. Classic methods view this problem from the perspective of intrinsic image decomposition, where an image is separated into reflectance and shading components. Rather than reason about reflectance and shading together, we learn to directly predict lightness differences between pixels. Large-scale training from human judgement data on relative reflectance, and patch representations built using deep networks, provide the foundation for our model. Benchmarked on the Intrinsic Images in the Wild dataset [4], our local lightness model achieves on-par performance with the state-of-the-art global lightness model, which incorporates multiple shading/reflectance priors and simultaneous reasoning between pairs of pixels in a dense conditional random field formulation.Keywords
This publication has 17 references indexed in Scilit:
- Caffe2014
- Non-parametric Filtering for Geometric Detail Extraction and Material Representation2013
- Multipath Sparse Coding Using Hierarchical Matching Pursuit2013
- Ground truth dataset and baseline evaluations for intrinsic image algorithms2009
- Oriented multiscale spatial filtering and contrast normalization: a parsimonious model of brightness induction in a continuum of stimuli including White, Howe and simultaneous brightness contrastVision Research, 2005
- Color lines: image specific color representation.2004
- Orthogonal matching pursuit: recursive function approximation with applications to wavelet decomposition2002
- Neural dynamics of 3-D surface perception: Figure-ground separation and lightness perceptionPerception & Psychophysics, 2000
- Determining lightness from an imageComputer Graphics and Image Processing, 1974
- Lightness and Retinex TheoryJournal of the Optical Society of America, 1971