Matches in SemOpenAlex for { <https://semopenalex.org/work/W4316259512> ?p ?o ?g. }
Showing items 1 to 68 of
68
with 100 items per page.
- W4316259512 endingPage "543" @default.
- W4316259512 startingPage "537" @default.
- W4316259512 abstract "Abstract. Today, three-dimensional reconstruction of objects has many applications in various fields, and therefore, choosing a suitable method for high resolution three-dimensional reconstruction is an important issue and displaying high-level details in three-dimensional models is a serious challenge in this field. Until now, active methods have been used for high-resolution three-dimensional reconstruction. But the problem of active three-dimensional reconstruction methods is that they require a light source close to the object. Shape from polarization (SfP) is one of the best solutions for high-resolution three-dimensional reconstruction of objects, which is a passive method and does not have the drawbacks of active methods. The changes in polarization of the reflected light from an object can be analyzed by using a polarization camera or locating polarizing filter in front of the digital camera and rotating the filter. Using this information, the surface normal can be reconstructed with high accuracy, which will lead to local reconstruction of the surface details. In this paper, an end-to-end deep learning approach has been presented to produce the surface normal of objects. In this method a benchmark dataset has been used to train the neural network and evaluate the results. The results have been evaluated quantitatively and qualitatively by other methods and under different lighting conditions. The MAE value (Mean-Angular-Error) has been used for results evaluation. The evaluations showed that the proposed method could accurately reconstruct the surface normal of objects with the lowest MAE value which is equal to 18.06 degree on the whole dataset, in comparison to previous physics-based methods which are between 41.44 and 49.03 degree." @default.
- W4316259512 created "2023-01-15" @default.
- W4316259512 creator A5005646468 @default.
- W4316259512 creator A5032845922 @default.
- W4316259512 creator A5085037233 @default.
- W4316259512 date "2023-01-14" @default.
- W4316259512 modified "2023-10-01" @default.
- W4316259512 title "SURFACE NORMAL RECONSTRUCTION USING POLARIZATION-UNET" @default.
- W4316259512 doi "https://doi.org/10.5194/isprs-annals-x-4-w1-2022-537-2023" @default.
- W4316259512 hasPublicationYear "2023" @default.
- W4316259512 type Work @default.
- W4316259512 citedByCount "0" @default.
- W4316259512 crossrefType "journal-article" @default.
- W4316259512 hasAuthorship W4316259512A5005646468 @default.
- W4316259512 hasAuthorship W4316259512A5032845922 @default.
- W4316259512 hasAuthorship W4316259512A5085037233 @default.
- W4316259512 hasBestOaLocation W43162595121 @default.
- W4316259512 hasConcept C118732077 @default.
- W4316259512 hasConcept C120665830 @default.
- W4316259512 hasConcept C121332964 @default.
- W4316259512 hasConcept C141379421 @default.
- W4316259512 hasConcept C147789679 @default.
- W4316259512 hasConcept C14860423 @default.
- W4316259512 hasConcept C154945302 @default.
- W4316259512 hasConcept C185592680 @default.
- W4316259512 hasConcept C205049153 @default.
- W4316259512 hasConcept C20885615 @default.
- W4316259512 hasConcept C2524010 @default.
- W4316259512 hasConcept C2776799497 @default.
- W4316259512 hasConcept C31972630 @default.
- W4316259512 hasConcept C33923547 @default.
- W4316259512 hasConcept C41008148 @default.
- W4316259512 hasConcept C45613198 @default.
- W4316259512 hasConceptScore W4316259512C118732077 @default.
- W4316259512 hasConceptScore W4316259512C120665830 @default.
- W4316259512 hasConceptScore W4316259512C121332964 @default.
- W4316259512 hasConceptScore W4316259512C141379421 @default.
- W4316259512 hasConceptScore W4316259512C147789679 @default.
- W4316259512 hasConceptScore W4316259512C14860423 @default.
- W4316259512 hasConceptScore W4316259512C154945302 @default.
- W4316259512 hasConceptScore W4316259512C185592680 @default.
- W4316259512 hasConceptScore W4316259512C205049153 @default.
- W4316259512 hasConceptScore W4316259512C20885615 @default.
- W4316259512 hasConceptScore W4316259512C2524010 @default.
- W4316259512 hasConceptScore W4316259512C2776799497 @default.
- W4316259512 hasConceptScore W4316259512C31972630 @default.
- W4316259512 hasConceptScore W4316259512C33923547 @default.
- W4316259512 hasConceptScore W4316259512C41008148 @default.
- W4316259512 hasConceptScore W4316259512C45613198 @default.
- W4316259512 hasLocation W43162595121 @default.
- W4316259512 hasOpenAccess W4316259512 @default.
- W4316259512 hasPrimaryLocation W43162595121 @default.
- W4316259512 hasRelatedWork W1999081819 @default.
- W4316259512 hasRelatedWork W2103597594 @default.
- W4316259512 hasRelatedWork W2382799321 @default.
- W4316259512 hasRelatedWork W2385144534 @default.
- W4316259512 hasRelatedWork W2517246325 @default.
- W4316259512 hasRelatedWork W2534204995 @default.
- W4316259512 hasRelatedWork W2892193095 @default.
- W4316259512 hasRelatedWork W2950926763 @default.
- W4316259512 hasRelatedWork W3194234974 @default.
- W4316259512 hasRelatedWork W4327521111 @default.
- W4316259512 hasVolume "X-4/W1-2022" @default.
- W4316259512 isParatext "false" @default.
- W4316259512 isRetracted "false" @default.
- W4316259512 workType "article" @default.