Ancuti, Codruta O.Codruta O.AncutiAncuti, CosminCosminAncutiVasluianu, Florin AlexandruFlorin AlexandruVasluianuTimofte, RaduRaduTimofteZhou, HanHanZhouDong, WeiWeiDongLiu, YangyiYangyiLiuChen, JunJunChenLiu, HuanHuanLiuLi, LiangyanLiangyanLiWu, ZijunZijunWuDong, YuboYuboDongLi, YuyanYuyanLiQiu, TianTianQiuHe, YuYuHeLu, YonghongYonghongLuWu, YinweiYinweiWuJiang, ZhenxiangZhenxiangJiangLiu, SonghuaSonghuaLiuYang, XingyiXingyiYangJing, YongchengYongchengJingBenjdira, BilelBilelBenjdiraAli, Anas M.Anas M.AliKoubaa, AnisAnisKoubaaYang, Hao HsiangHao HsiangYangChen, I. HsiangI. HsiangChenWEI-TING CHENHuang, Zhi KaiZhi KaiHuangChen, Yi ChungYi ChungChenHsieh, Chia HsuanChia HsuanHsiehChang, Hua EnHua EnChangChiang, Yuan ChunYuan ChunChiangSY-YEN KUOGuo, YuYuGuoGao, YuanYuanGaoLiu, Ryan WenRyan WenLiuLu, YuxuYuxuLuQu, JingxiangJingxiangQuHe, ShengfengShengfengHeRen, WenqiWenqiRenHoang, TrungTrungHoangZhang, HaichuanHaichuanZhangYazdani, AmirsaeedAmirsaeedYazdaniMonga, VishalVishalMongaYang, LehanLehanYangWu, Alex JiahaoAlex JiahaoWuMai, TianchengTianchengMaiCong, XiaofengXiaofengCongYin, XuemengXuemengYinYin, XuefeiXuefeiYinEmad, HazimHazimEmadAbdallah, AhmedAhmedAbdallahYasser, YahyaYahyaYasserElshahat, DaliaDaliaElshahatElbaz, EsraaEsraaElbazLi, ZhanZhanLiKuang, WenqingWenqingKuangLuo, ZiweiZiweiLuoGustafsson, Fredrik K.Fredrik K.GustafssonZhao, ZhengZhengZhaoSjölund, JensJensSjölundSchön, Thomas B.Thomas B.SchönZhang, ZhaoZhaoZhangWei, YanyanYanyanWeiWang, JunhuJunhuWangZhao, SuiyiSuiyiZhaoZheng, HuanHuanZhengGuo, JinJinGuoSun, YangfanYangfanSunLiu, TianliTianliLiuHao, DejunDejunHaoJiang, KuiKuiJiangSarvaiya, AnjaliAnjaliSarvaiyaPrajapati, KalpeshKalpeshPrajapatiPatra, RatnadeepRatnadeepPatraBarik, PragneshPragneshBarikRathod, ChaitanyaChaitanyaRathodUpla, KishorKishorUplaRaja, KiranKiranRajaRamachandra, RaghavendraRaghavendraRamachandraBusch, ChristophChristophBusch2023-10-192023-10-192023-01-01979835030249321607508https://scholars.lib.ntu.edu.tw/handle/123456789/636205This study assesses the outcomes of the NTIRE 2023 Challenge on Non-Homogeneous Dehazing, wherein novel techniques were proposed and evaluated on new image dataset called HD-NH-HAZE. The HD-NH-HAZE dataset contains 50 high resolution pairs of real-life outdoor images featuring nonhomogeneous hazy images and corresponding haze-free images of the same scene. The nonhomogeneous haze was simulated using a professional setup that replicated real-world conditions of hazy scenarios. The competition had 246 participants and 17 teams submitted solutions for the final testing phase. The proposed solutions demonstrated the cutting-edge in image dehazing technology.[SDGs]SDG12conference paper10.1109/CVPRW59228.2023.001802-s2.0-85170828355https://api.elsevier.com/content/abstract/scopus_id/85170828355