From pixels to physics: Probabilistic color de-rendering

Consumer digital cameras use tone-mapping to produce compact, narrow-gamut images that are nonetheless visually pleasing. In doing so, they discard or distort substantial radiometric signal that could otherwise be used for computer vision. Existing methods attempt to undo these effects through deterministic maps that de-render the reported narrow-gamut colors back to their original wide-gamut sensor measurements. Deterministic approaches are unreliable, however, because the reverse narrow-to-wide mapping is one-to-many and has inherent uncertainty. Our solution is to use probabilistic maps, providing uncertainty estimates useful to many applications. We use a nonparametric Bayesian regression technique—local Gaussian process regression—to learn for each pixel’s narrow-gamut color a probability distribution over the scene colors that could have created it. Using a variety of consumer cameras we show that these distributions, once learned from training data, are effective in simpl...

• Type: Journal
• Year: 2012
• Where: CVPR
• Authors: Ying Xiong, Kate Saenko, Trevor Darrell, Todd Zickler
• Keywords: Computer Vision, Cvpr 2012, Deterministic Approaches, Sensor Measurements, Wide Gamut