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.
Buzzelli, M., Riva, R., Bianco, S., Schettini, R. (2021). Consensus-driven illuminant estimation with GANs. In Proceedings of a meeting held 2-6 November 2020, Rome, Italy. SPIE [10.1117/12.2587589].
Consensus-driven illuminant estimation with GANs
Buzzelli, Marco
;Bianco, Simone;Schettini, Raimondo
2021
Abstract
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.
| File | Dimensione | Formato | |
|---|---|---|---|
|
2020b_Consensus-driven_Illuminant_Estimation_with_GANs.pdf
Solo gestori archivio
Tipologia di allegato:
Publisher’s Version (Version of Record, VoR)
Dimensione
553.26 kB
Formato
Adobe PDF
|
553.26 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
