Matches in SemOpenAlex for { <https://semopenalex.org/work/W3208308045> ?p ?o ?g. }
- W3208308045 endingPage "9149" @default.
- W3208308045 startingPage "9136" @default.
- W3208308045 abstract "Due to the lack of natural scene and haze prior information, it is greatly challenging to completely remove the haze from a single image without distorting its visual content. Fortunately, the real-world haze usually presents non-homogeneous distribution, which provides us with many valuable clues in partial well-preserved regions. In this paper, we propose a Non-Homogeneous Haze Removal Network (NHRN) via artificial scene prior and bidimensional graph reasoning. Firstly, we employ the gamma correction iteratively to simulate artificial multiple shots under different exposure conditions, whose haze degrees are different and enrich the underlying scene prior. Secondly, beyond utilizing the local neighboring relationship, we build a bidimensional graph reasoning module to conduct non-local filtering in the spatial and channel dimensions of feature maps, which models their long-range dependency and propagates the natural scene prior between the well-preserved nodes and the nodes contaminated by haze. To the best of our knowledge, this is the first exploration to remove non-homogeneous haze via the graph reasoning based framework. We evaluate our method on different benchmark datasets. The results demonstrate that our method achieves superior performance over many state-of-the-art algorithms for both the single image dehazing and hazy image understanding tasks. The source code of the proposed NHRN is available on https://github.com/whrws/NHRNet." @default.
- W3208308045 created "2021-11-08" @default.
- W3208308045 creator A5008589907 @default.
- W3208308045 creator A5016590465 @default.
- W3208308045 creator A5022134460 @default.
- W3208308045 creator A5044954967 @default.
- W3208308045 creator A5071032466 @default.
- W3208308045 creator A5075737786 @default.
- W3208308045 creator A5077165659 @default.
- W3208308045 date "2021-01-01" @default.
- W3208308045 modified "2023-10-14" @default.
- W3208308045 title "Non-Homogeneous Haze Removal via Artificial Scene Prior and Bidimensional Graph Reasoning" @default.
- W3208308045 cites W1552073401 @default.
- W3208308045 cites W1979666307 @default.
- W3208308045 cites W1998363013 @default.
- W3208308045 cites W2003709967 @default.
- W3208308045 cites W2025360228 @default.
- W3208308045 cites W2028990532 @default.
- W3208308045 cites W2097073572 @default.
- W3208308045 cites W2097900287 @default.
- W3208308045 cites W2109616376 @default.
- W3208308045 cites W2110644821 @default.
- W3208308045 cites W2114867966 @default.
- W3208308045 cites W2121880036 @default.
- W3208308045 cites W2128254161 @default.
- W3208308045 cites W2141030717 @default.
- W3208308045 cites W2141200610 @default.
- W3208308045 cites W2147318913 @default.
- W3208308045 cites W2156936307 @default.
- W3208308045 cites W2194775991 @default.
- W3208308045 cites W2256362396 @default.
- W3208308045 cites W2340897893 @default.
- W3208308045 cites W2519481857 @default.
- W3208308045 cites W2560023338 @default.
- W3208308045 cites W2748021867 @default.
- W3208308045 cites W2776638780 @default.
- W3208308045 cites W2779176852 @default.
- W3208308045 cites W2792830341 @default.
- W3208308045 cites W2806331055 @default.
- W3208308045 cites W2887964057 @default.
- W3208308045 cites W2890489646 @default.
- W3208308045 cites W2894938704 @default.
- W3208308045 cites W2899026108 @default.
- W3208308045 cites W2918431349 @default.
- W3208308045 cites W2948519073 @default.
- W3208308045 cites W2962754725 @default.
- W3208308045 cites W2962782447 @default.
- W3208308045 cites W2962785568 @default.
- W3208308045 cites W2963085671 @default.
- W3208308045 cites W2963152299 @default.
- W3208308045 cites W2963306157 @default.
- W3208308045 cites W2963319519 @default.
- W3208308045 cites W2963928582 @default.
- W3208308045 cites W2964115968 @default.
- W3208308045 cites W2979261558 @default.
- W3208308045 cites W2985030998 @default.
- W3208308045 cites W2990007814 @default.
- W3208308045 cites W2997210448 @default.
- W3208308045 cites W3034278302 @default.
- W3208308045 cites W3034961799 @default.
- W3208308045 cites W3035345812 @default.
- W3208308045 cites W3035601380 @default.
- W3208308045 cites W3035665982 @default.
- W3208308045 cites W3091357435 @default.
- W3208308045 cites W3109202794 @default.
- W3208308045 cites W3110069174 @default.
- W3208308045 cites W3124306134 @default.
- W3208308045 cites W3124953441 @default.
- W3208308045 cites W3131604210 @default.
- W3208308045 cites W639708223 @default.
- W3208308045 doi "https://doi.org/10.1109/tip.2021.3122806" @default.
- W3208308045 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34735342" @default.
- W3208308045 hasPublicationYear "2021" @default.
- W3208308045 type Work @default.
- W3208308045 sameAs 3208308045 @default.
- W3208308045 citedByCount "4" @default.
- W3208308045 countsByYear W32083080452022 @default.
- W3208308045 countsByYear W32083080452023 @default.
- W3208308045 crossrefType "journal-article" @default.
- W3208308045 hasAuthorship W3208308045A5008589907 @default.
- W3208308045 hasAuthorship W3208308045A5016590465 @default.
- W3208308045 hasAuthorship W3208308045A5022134460 @default.
- W3208308045 hasAuthorship W3208308045A5044954967 @default.
- W3208308045 hasAuthorship W3208308045A5071032466 @default.
- W3208308045 hasAuthorship W3208308045A5075737786 @default.
- W3208308045 hasAuthorship W3208308045A5077165659 @default.
- W3208308045 hasBestOaLocation W32083080452 @default.
- W3208308045 hasConcept C114614502 @default.
- W3208308045 hasConcept C121332964 @default.
- W3208308045 hasConcept C132525143 @default.
- W3208308045 hasConcept C13280743 @default.
- W3208308045 hasConcept C153180895 @default.
- W3208308045 hasConcept C153294291 @default.
- W3208308045 hasConcept C154945302 @default.
- W3208308045 hasConcept C185798385 @default.
- W3208308045 hasConcept C205649164 @default.
- W3208308045 hasConcept C31972630 @default.
- W3208308045 hasConcept C33923547 @default.