Matches in SemOpenAlex for { <https://semopenalex.org/work/W2978788458> ?p ?o ?g. }
- W2978788458 endingPage "1617" @default.
- W2978788458 startingPage "1606" @default.
- W2978788458 abstract "Learning based depth estimation from light field has made significant progresses in recent years. However, most existing approaches are under the supervised framework, which requires vast quantities of ground-truth depth data for training. Furthermore, accurate depth maps of light field are hardly available except for a few synthetic datasets. In this paper, we exploit the multi-orientation epipolar geometry of light field and propose an unsupervised monocular depth estimation network. It predicts depth from the central view of light field without any ground-truth information. Inspired by the inherent depth cues and geometry constraints of light field, we then introduce three novel unsupervised loss functions: photometric loss, defocus loss and symmetry loss. We have evaluated our method on a public 4D light field synthetic dataset. As the first unsupervised method published in the 4D Light Field Benchmark website, our method can achieve satisfactory performance in most error metrics. Comparison experiments with two state-of-the-art unsupervised methods demonstrate the superiority of our method. We also prove the effectiveness and generality of our method on real-world light-field images." @default.
- W2978788458 created "2019-10-10" @default.
- W2978788458 creator A5036542312 @default.
- W2978788458 creator A5064059062 @default.
- W2978788458 creator A5067114207 @default.
- W2978788458 creator A5067452827 @default.
- W2978788458 creator A5074260102 @default.
- W2978788458 date "2020-01-01" @default.
- W2978788458 modified "2023-09-30" @default.
- W2978788458 title "Unsupervised Monocular Depth Estimation From Light Field Image" @default.
- W2978788458 cites W1803059841 @default.
- W2978788458 cites W1914596733 @default.
- W2978788458 cites W2007165614 @default.
- W2978788458 cites W2043408784 @default.
- W2978788458 cites W2079176966 @default.
- W2978788458 cites W2123042594 @default.
- W2978788458 cites W2128359381 @default.
- W2978788458 cites W2133515844 @default.
- W2978788458 cites W2133665775 @default.
- W2978788458 cites W2149694199 @default.
- W2978788458 cites W2155763342 @default.
- W2978788458 cites W2194775991 @default.
- W2978788458 cites W2200825767 @default.
- W2978788458 cites W2211024058 @default.
- W2978788458 cites W2289524987 @default.
- W2978788458 cites W2296677960 @default.
- W2978788458 cites W2337243791 @default.
- W2978788458 cites W2341651707 @default.
- W2978788458 cites W2342420672 @default.
- W2978788458 cites W2440384215 @default.
- W2978788458 cites W2464308330 @default.
- W2978788458 cites W2471061117 @default.
- W2978788458 cites W2520707372 @default.
- W2978788458 cites W2548527721 @default.
- W2978788458 cites W2551052086 @default.
- W2978788458 cites W2737842117 @default.
- W2978788458 cites W2741694910 @default.
- W2978788458 cites W2751225115 @default.
- W2978788458 cites W2752279250 @default.
- W2978788458 cites W2753230437 @default.
- W2978788458 cites W2776033207 @default.
- W2978788458 cites W2778641202 @default.
- W2978788458 cites W2779124836 @default.
- W2978788458 cites W2779696137 @default.
- W2978788458 cites W2783516823 @default.
- W2978788458 cites W2790316230 @default.
- W2978788458 cites W2798270832 @default.
- W2978788458 cites W2798487245 @default.
- W2978788458 cites W2897264375 @default.
- W2978788458 cites W2902024778 @default.
- W2978788458 cites W2902536616 @default.
- W2978788458 cites W2962864875 @default.
- W2978788458 cites W2963583471 @default.
- W2978788458 cites W2963872754 @default.
- W2978788458 cites W2964178790 @default.
- W2978788458 cites W3100388886 @default.
- W2978788458 cites W764651262 @default.
- W2978788458 doi "https://doi.org/10.1109/tip.2019.2944343" @default.
- W2978788458 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/31603783" @default.
- W2978788458 hasPublicationYear "2020" @default.
- W2978788458 type Work @default.
- W2978788458 sameAs 2978788458 @default.
- W2978788458 citedByCount "30" @default.
- W2978788458 countsByYear W29787884582020 @default.
- W2978788458 countsByYear W29787884582021 @default.
- W2978788458 countsByYear W29787884582022 @default.
- W2978788458 countsByYear W29787884582023 @default.
- W2978788458 crossrefType "journal-article" @default.
- W2978788458 hasAuthorship W2978788458A5036542312 @default.
- W2978788458 hasAuthorship W2978788458A5064059062 @default.
- W2978788458 hasAuthorship W2978788458A5067114207 @default.
- W2978788458 hasAuthorship W2978788458A5067452827 @default.
- W2978788458 hasAuthorship W2978788458A5074260102 @default.
- W2978788458 hasConcept C108583219 @default.
- W2978788458 hasConcept C115961682 @default.
- W2978788458 hasConcept C127313418 @default.
- W2978788458 hasConcept C13280743 @default.
- W2978788458 hasConcept C146849305 @default.
- W2978788458 hasConcept C153180895 @default.
- W2978788458 hasConcept C154945302 @default.
- W2978788458 hasConcept C185798385 @default.
- W2978788458 hasConcept C202444582 @default.
- W2978788458 hasConcept C23379248 @default.
- W2978788458 hasConcept C31972630 @default.
- W2978788458 hasConcept C33923547 @default.
- W2978788458 hasConcept C41008148 @default.
- W2978788458 hasConcept C48983235 @default.
- W2978788458 hasConcept C65909025 @default.
- W2978788458 hasConcept C8038995 @default.
- W2978788458 hasConcept C9652623 @default.
- W2978788458 hasConceptScore W2978788458C108583219 @default.
- W2978788458 hasConceptScore W2978788458C115961682 @default.
- W2978788458 hasConceptScore W2978788458C127313418 @default.
- W2978788458 hasConceptScore W2978788458C13280743 @default.
- W2978788458 hasConceptScore W2978788458C146849305 @default.
- W2978788458 hasConceptScore W2978788458C153180895 @default.
- W2978788458 hasConceptScore W2978788458C154945302 @default.
- W2978788458 hasConceptScore W2978788458C185798385 @default.