?url_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Adc&rft.title=AutoColor%3A+learned+light+power+control+for+multi-color+holograms&rft.creator=Zhan%2C+Y&rft.creator=Kavakll%2C+K&rft.creator=Urey%2C+H&rft.creator=Sun%2C+Q&rft.creator=Ak%C5%9Fit%2C+K&rft.description=Multi-color+holograms+rely+on+simultaneous+illumination+from+multiple+light+sources.+These+multi-color+holograms+could+utilize+light+sources+better+than+conventional+single-color+holograms+and+can+improve+the+dynamic+range+of+holographic+displays.+In+this+letter%2C+we+introduce+AutoColor%2C+the+first+learned+method+for+estimating+the+optimal+light+source+powers+required+for+illuminating+multi-color+holograms.+For+this+purpose%2C+we+establish+the+first+multi-color+hologram+dataset+using+synthetic+images+and+their+depth+information.+We+generate+these+synthetic+images+using+a+trending+pipeline+combining+generative%2C+large+language%2C+and+monocular+depth+estimation+models.+Finally%2C+we+train+our+learned+model+using+our+dataset+and+experimentally+demonstrate+that+AutoColor+significantly+decreases+the+number+of+steps+required+to+optimize+multi-color+holograms+from+%3E+1000+to+70+iteration+steps+without+compromising+image+quality.&rft.publisher=SPIE&rft.contributor=Hua%2C+Hong&rft.contributor=Argaman%2C+Naamah&rft.contributor=Nikolov%2C+Daniel+K&rft.date=2024-01-01&rft.type=Proceedings+paper&rft.language=eng&rft.source=+++++In%3A+Hua%2C+Hong+and+Argaman%2C+Naamah+and+Nikolov%2C+Daniel+K%2C+(eds.)+Proceedings+of+SPIE+-+The+International+Society+for+Optical+Engineering.++(pp.+129130I).++SPIE%3A+San+Francisco%2C+CA%2C+USA.+(2024)+++++&rft.format=text&rft.identifier=https%3A%2F%2Fdiscovery.ucl.ac.uk%2Fid%2Feprint%2F10192175%2F2%2FAksit_129130I.pdf&rft.identifier=https%3A%2F%2Fdiscovery.ucl.ac.uk%2Fid%2Feprint%2F10192175%2F&rft.rights=open