FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3186204905> ?p ?o ?g. }

• W3186204905 endingPage "17" @default.
• W3186204905 startingPage "1" @default.
• W3186204905 abstract "This article investigates the limitations of single image depth prediction (SIDP) under different lighting conditions. Besides that, it also offers a new approach to obtain the ideal condition for SIDP. To satisfy the data requirement, we exploit a photometric stereo dataset consisting of several images of an object under different light properties. In this work, we used a dataset of ancient Roman coins captured under 54 different lighting conditions to illustrate how the approach is affected by them. This dataset emulates many lighting variances with a different state of shading and reflectance common in the natural environment. The ground truth depth data in the dataset was obtained using the stereo photometric method and used as training data. We investigated the capabilities of three different state-of-the-art methods to reconstruct ancient Roman coins with different lighting scenarios. The first investigation compares the performance of a given network using previously trained data to check cross-domains performance. Second, the model is fine-tuned from pre-trained data and trained using 70% of the ancient Roman coin dataset. Both models are tested on the remaining 30% of the data. As evaluation metrics, root mean square error and visual inspection are used. As a result, the methods show different characteristic results based on the lighting condition of the test data. Overall, they perform better at 51° and 71° angles of light, so-called ideal condition afterward. However, they perform worse at 13° and 32° because of the high density of shadows. They also cannot reach the best performance at 82° caused by the reflection that appears on the image. Based on these findings, we propose a new approach to reduce the shadows and reflections on the image using intrinsic image decomposition to achieve a synthetic ideal condition. Based on the results of synthetic images, this approach can enhance the performance of SIDP. For some state-of-the-art methods, it also achieves better results than previous original RGB images." @default.
• W3186204905 created "2021-08-02" @default.
• W3186204905 creator A5019162549 @default.
• W3186204905 creator A5028278845 @default.
• W3186204905 creator A5032323385 @default.
• W3186204905 creator A5050960750 @default.
• W3186204905 creator A5074305874 @default.
• W3186204905 date "2021-07-16" @default.
• W3186204905 modified "2023-10-05" @default.
• W3186204905 title "Investigation of Single Image Depth Prediction Under Different Lighting Conditions" @default.
• W3186204905 cites W125693051 @default.
• W3186204905 cites W1803059841 @default.
• W3186204905 cites W1901129140 @default.
• W3186204905 cites W2112796928 @default.
• W3186204905 cites W2115579991 @default.
• W3186204905 cites W2132947399 @default.
• W3186204905 cites W2134019950 @default.
• W3186204905 cites W2216090464 @default.
• W3186204905 cites W2245606284 @default.
• W3186204905 cites W2303211814 @default.
• W3186204905 cites W2412782625 @default.
• W3186204905 cites W2560722161 @default.
• W3186204905 cites W2794572859 @default.
• W3186204905 cites W2889002172 @default.
• W3186204905 cites W2891279733 @default.
• W3186204905 cites W2960206397 @default.
• W3186204905 cites W2962741876 @default.
• W3186204905 cites W2963110069 @default.
• W3186204905 cites W2963488291 @default.
• W3186204905 cites W2964108477 @default.
• W3186204905 cites W2982604968 @default.
• W3186204905 cites W3009020965 @default.
• W3186204905 cites W3011621377 @default.
• W3186204905 doi "https://doi.org/10.1145/3465742" @default.
• W3186204905 hasPublicationYear "2021" @default.
• W3186204905 type Work @default.
• W3186204905 sameAs 3186204905 @default.
• W3186204905 citedByCount "2" @default.
• W3186204905 countsByYear W31862049052023 @default.
• W3186204905 crossrefType "journal-article" @default.
• W3186204905 hasAuthorship W3186204905A5019162549 @default.
• W3186204905 hasAuthorship W3186204905A5028278845 @default.
• W3186204905 hasAuthorship W3186204905A5032323385 @default.
• W3186204905 hasAuthorship W3186204905A5050960750 @default.
• W3186204905 hasAuthorship W3186204905A5074305874 @default.
• W3186204905 hasConcept C105795698 @default.
• W3186204905 hasConcept C111472728 @default.
• W3186204905 hasConcept C115961682 @default.
• W3186204905 hasConcept C138885662 @default.
• W3186204905 hasConcept C139945424 @default.
• W3186204905 hasConcept C146849305 @default.
• W3186204905 hasConcept C154945302 @default.
• W3186204905 hasConcept C165696696 @default.
• W3186204905 hasConcept C2776639384 @default.
• W3186204905 hasConcept C31972630 @default.
• W3186204905 hasConcept C33923547 @default.
• W3186204905 hasConcept C38652104 @default.
• W3186204905 hasConcept C41008148 @default.
• W3186204905 hasConcept C44365914 @default.
• W3186204905 hasConceptScore W3186204905C105795698 @default.
• W3186204905 hasConceptScore W3186204905C111472728 @default.
• W3186204905 hasConceptScore W3186204905C115961682 @default.
• W3186204905 hasConceptScore W3186204905C138885662 @default.
• W3186204905 hasConceptScore W3186204905C139945424 @default.
• W3186204905 hasConceptScore W3186204905C146849305 @default.
• W3186204905 hasConceptScore W3186204905C154945302 @default.
• W3186204905 hasConceptScore W3186204905C165696696 @default.
• W3186204905 hasConceptScore W3186204905C2776639384 @default.
• W3186204905 hasConceptScore W3186204905C31972630 @default.
• W3186204905 hasConceptScore W3186204905C33923547 @default.
• W3186204905 hasConceptScore W3186204905C38652104 @default.
• W3186204905 hasConceptScore W3186204905C41008148 @default.
• W3186204905 hasConceptScore W3186204905C44365914 @default.
• W3186204905 hasIssue "4" @default.
• W3186204905 hasLocation W31862049051 @default.
• W3186204905 hasOpenAccess W3186204905 @default.
• W3186204905 hasPrimaryLocation W31862049051 @default.
• W3186204905 hasRelatedWork W1554604122 @default.
• W3186204905 hasRelatedWork W1632903234 @default.
• W3186204905 hasRelatedWork W2043933577 @default.
• W3186204905 hasRelatedWork W2103381853 @default.
• W3186204905 hasRelatedWork W2138334472 @default.
• W3186204905 hasRelatedWork W2156736396 @default.
• W3186204905 hasRelatedWork W2158018118 @default.
• W3186204905 hasRelatedWork W2744088300 @default.
• W3186204905 hasRelatedWork W3004045746 @default.
• W3186204905 hasRelatedWork W3194234974 @default.
• W3186204905 hasVolume "14" @default.
• W3186204905 isParatext "false" @default.
• W3186204905 isRetracted "false" @default.
• W3186204905 magId "3186204905" @default.
• W3186204905 workType "article" @default.