Matches in SemOpenAlex for { <https://semopenalex.org/work/W2963530785> ?p ?o ?g. }
- W2963530785 abstract "We present a novel deep learning architecture for fusing static multi-exposure images. Current multi-exposure fusion (MEF) approaches use hand-crafted features to fuse input sequence. However, the weak hand-crafted representations are not robust to varying input conditions. Moreover, they perform poorly for extreme exposure image pairs. Thus, it is highly desirable to have a method that is robust to varying input conditions and capable of handling extreme exposure without artifacts. Deep representations have known to be robust to input conditions and have shown phenomenal performance in a supervised setting. However, the stumbling block in using deep learning for MEF was the lack of sufficient training data and an oracle to provide the ground-truth for supervision. To address the above issues, we have gathered a large dataset of multi-exposure image stacks for training and to circumvent the need for ground truth images, we propose an unsupervised deep learning framework for MEF utilizing a no-reference quality metric as loss function. The proposed approach uses a novel CNN architecture trained to learn the fusion operation without reference ground truth image. The model fuses a set of common low level features extracted from each image to generate artifact-free perceptually pleasing results. We perform extensive quantitative and qualitative evaluation and show that the proposed technique outperforms existing state-of-the-art approaches for a variety of natural images." @default.
- W2963530785 created "2019-07-30" @default.
- W2963530785 creator A5035393324 @default.
- W2963530785 creator A5062096014 @default.
- W2963530785 creator A5083410137 @default.
- W2963530785 date "2017-10-01" @default.
- W2963530785 modified "2023-10-10" @default.
- W2963530785 title "DeepFuse: A Deep Unsupervised Approach for Exposure Fusion with Extreme Exposure Image Pairs" @default.
- W2963530785 cites W1580436348 @default.
- W2963530785 cites W1933349210 @default.
- W2963530785 cites W1991659632 @default.
- W2963530785 cites W2015908134 @default.
- W2963530785 cites W2032959374 @default.
- W2963530785 cites W2035234709 @default.
- W2963530785 cites W2039465985 @default.
- W2963530785 cites W2083511445 @default.
- W2963530785 cites W2087366239 @default.
- W2963530785 cites W2102584639 @default.
- W2963530785 cites W2116702374 @default.
- W2963530785 cites W2132746638 @default.
- W2963530785 cites W2133665775 @default.
- W2963530785 cites W2136001449 @default.
- W2963530785 cites W2160057126 @default.
- W2963530785 cites W2163932540 @default.
- W2963530785 cites W2194775991 @default.
- W2963530785 cites W2296478018 @default.
- W2963530785 cites W2400231654 @default.
- W2963530785 cites W2575511118 @default.
- W2963530785 cites W2919115771 @default.
- W2963530785 cites W2963150697 @default.
- W2963530785 cites W2964135133 @default.
- W2963530785 doi "https://doi.org/10.1109/iccv.2017.505" @default.
- W2963530785 hasPublicationYear "2017" @default.
- W2963530785 type Work @default.
- W2963530785 sameAs 2963530785 @default.
- W2963530785 citedByCount "336" @default.
- W2963530785 countsByYear W29635307852018 @default.
- W2963530785 countsByYear W29635307852019 @default.
- W2963530785 countsByYear W29635307852020 @default.
- W2963530785 countsByYear W29635307852021 @default.
- W2963530785 countsByYear W29635307852022 @default.
- W2963530785 countsByYear W29635307852023 @default.
- W2963530785 crossrefType "proceedings-article" @default.
- W2963530785 hasAuthorship W2963530785A5035393324 @default.
- W2963530785 hasAuthorship W2963530785A5062096014 @default.
- W2963530785 hasAuthorship W2963530785A5083410137 @default.
- W2963530785 hasBestOaLocation W29635307852 @default.
- W2963530785 hasConcept C108583219 @default.
- W2963530785 hasConcept C115903868 @default.
- W2963530785 hasConcept C115961682 @default.
- W2963530785 hasConcept C119599485 @default.
- W2963530785 hasConcept C119857082 @default.
- W2963530785 hasConcept C127413603 @default.
- W2963530785 hasConcept C141353440 @default.
- W2963530785 hasConcept C146849305 @default.
- W2963530785 hasConcept C153180895 @default.
- W2963530785 hasConcept C154945302 @default.
- W2963530785 hasConcept C162324750 @default.
- W2963530785 hasConcept C176217482 @default.
- W2963530785 hasConcept C177264268 @default.
- W2963530785 hasConcept C199360897 @default.
- W2963530785 hasConcept C21547014 @default.
- W2963530785 hasConcept C2524010 @default.
- W2963530785 hasConcept C2777210771 @default.
- W2963530785 hasConcept C31972630 @default.
- W2963530785 hasConcept C33923547 @default.
- W2963530785 hasConcept C41008148 @default.
- W2963530785 hasConcept C55166926 @default.
- W2963530785 hasConcept C69744172 @default.
- W2963530785 hasConceptScore W2963530785C108583219 @default.
- W2963530785 hasConceptScore W2963530785C115903868 @default.
- W2963530785 hasConceptScore W2963530785C115961682 @default.
- W2963530785 hasConceptScore W2963530785C119599485 @default.
- W2963530785 hasConceptScore W2963530785C119857082 @default.
- W2963530785 hasConceptScore W2963530785C127413603 @default.
- W2963530785 hasConceptScore W2963530785C141353440 @default.
- W2963530785 hasConceptScore W2963530785C146849305 @default.
- W2963530785 hasConceptScore W2963530785C153180895 @default.
- W2963530785 hasConceptScore W2963530785C154945302 @default.
- W2963530785 hasConceptScore W2963530785C162324750 @default.
- W2963530785 hasConceptScore W2963530785C176217482 @default.
- W2963530785 hasConceptScore W2963530785C177264268 @default.
- W2963530785 hasConceptScore W2963530785C199360897 @default.
- W2963530785 hasConceptScore W2963530785C21547014 @default.
- W2963530785 hasConceptScore W2963530785C2524010 @default.
- W2963530785 hasConceptScore W2963530785C2777210771 @default.
- W2963530785 hasConceptScore W2963530785C31972630 @default.
- W2963530785 hasConceptScore W2963530785C33923547 @default.
- W2963530785 hasConceptScore W2963530785C41008148 @default.
- W2963530785 hasConceptScore W2963530785C55166926 @default.
- W2963530785 hasConceptScore W2963530785C69744172 @default.
- W2963530785 hasLocation W29635307851 @default.
- W2963530785 hasLocation W29635307852 @default.
- W2963530785 hasLocation W29635307853 @default.
- W2963530785 hasOpenAccess W2963530785 @default.
- W2963530785 hasPrimaryLocation W29635307851 @default.
- W2963530785 hasRelatedWork W1988829224 @default.
- W2963530785 hasRelatedWork W2010729749 @default.
- W2963530785 hasRelatedWork W2134473361 @default.
- W2963530785 hasRelatedWork W2169891923 @default.