Deep neural networks trained for estimating albedo and illumination achieve lightness constancy differently than human observers.
Alban Flachot, Jaykishan Y. Patel, Thomas S. A. Wallis, Marcus A. Brubaker, David H. Brainard, Richard F. Murray
This study compares how deep neural networks and human observers achieve lightness constancy by estimating albedo and illumination in controlled conditions.
Journal of Vision · Feb 18, 2026Peer-reviewedNeuroscience