Consensus-driven illuminant estimation with GANs
Marco Buzzelli, Riccardo E. M. Riva, Simone Bianco, Raimondo Schettini · 2021
We present a method for illuminant estimation that exploits a generative adversarial network architecture to generate a spatially-varying illuminant map. This map is then transformed by consensus into a global illuminant estimation, in the form of a single RGB triplet. To this end, different consensus strategies are designed and compared in this paper. The best solution won second place in the 2nd International Illumination Estimation Challenge, specifically for the indoor track.