Matches in SemOpenAlex for { <https://semopenalex.org/work/W4383109031> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W4383109031 abstract "Surface normal holds significant importance in visual environmental perception, serving as a source of rich geometric information. However, the state-of-the-art (SoTA) surface normal estimators (SNEs) generally suffer from an unsatisfactory trade-off between efficiency and accuracy. To resolve this dilemma, this paper first presents a superfast depth-to-normal translator (D2NT), which can directly translate depth images into surface normal maps without calculating 3D coordinates. We then propose a discontinuity-aware gradient (DAG) filter, which adaptively generates gradient convolution kernels to improve depth gradient estimation. Finally, we propose a surface normal refinement module that can easily be integrated into any depth-to-normal SNEs, substantially improving the surface normal estimation accuracy. Our proposed algorithm demonstrates the best accuracy among all other existing real-time SNEs and achieves the SoTA trade-off between efficiency and accuracy." @default.
- W4383109031 created "2023-07-05" @default.
- W4383109031 creator A5013031996 @default.
- W4383109031 creator A5019023411 @default.
- W4383109031 creator A5025879011 @default.
- W4383109031 creator A5038867899 @default.
- W4383109031 creator A5073789459 @default.
- W4383109031 date "2023-05-29" @default.
- W4383109031 modified "2023-10-16" @default.
- W4383109031 title "D2NT: A High-Performing Depth-to-Normal Translator" @default.
- W4383109031 cites W2058606296 @default.
- W4383109031 cites W2074693620 @default.
- W4383109031 cites W2136893407 @default.
- W4383109031 cites W2167387804 @default.
- W4383109031 cites W2174199761 @default.
- W4383109031 cites W2798927139 @default.
- W4383109031 cites W2986519585 @default.
- W4383109031 cites W3025191362 @default.
- W4383109031 cites W3048686556 @default.
- W4383109031 cites W3082498369 @default.
- W4383109031 cites W3105136107 @default.
- W4383109031 cites W3130089842 @default.
- W4383109031 cites W3134257222 @default.
- W4383109031 cites W3137498582 @default.
- W4383109031 cites W4321512590 @default.
- W4383109031 doi "https://doi.org/10.1109/icra48891.2023.10161000" @default.
- W4383109031 hasPublicationYear "2023" @default.
- W4383109031 type Work @default.
- W4383109031 citedByCount "1" @default.
- W4383109031 crossrefType "proceedings-article" @default.
- W4383109031 hasAuthorship W4383109031A5013031996 @default.
- W4383109031 hasAuthorship W4383109031A5019023411 @default.
- W4383109031 hasAuthorship W4383109031A5025879011 @default.
- W4383109031 hasAuthorship W4383109031A5038867899 @default.
- W4383109031 hasAuthorship W4383109031A5073789459 @default.
- W4383109031 hasBestOaLocation W43831090312 @default.
- W4383109031 hasConcept C105795698 @default.
- W4383109031 hasConcept C11413529 @default.
- W4383109031 hasConcept C118732077 @default.
- W4383109031 hasConcept C134306372 @default.
- W4383109031 hasConcept C154945302 @default.
- W4383109031 hasConcept C15627037 @default.
- W4383109031 hasConcept C185429906 @default.
- W4383109031 hasConcept C2524010 @default.
- W4383109031 hasConcept C2776799497 @default.
- W4383109031 hasConcept C2777042112 @default.
- W4383109031 hasConcept C31972630 @default.
- W4383109031 hasConcept C33923547 @default.
- W4383109031 hasConcept C41008148 @default.
- W4383109031 hasConcept C45347329 @default.
- W4383109031 hasConcept C50644808 @default.
- W4383109031 hasConceptScore W4383109031C105795698 @default.
- W4383109031 hasConceptScore W4383109031C11413529 @default.
- W4383109031 hasConceptScore W4383109031C118732077 @default.
- W4383109031 hasConceptScore W4383109031C134306372 @default.
- W4383109031 hasConceptScore W4383109031C154945302 @default.
- W4383109031 hasConceptScore W4383109031C15627037 @default.
- W4383109031 hasConceptScore W4383109031C185429906 @default.
- W4383109031 hasConceptScore W4383109031C2524010 @default.
- W4383109031 hasConceptScore W4383109031C2776799497 @default.
- W4383109031 hasConceptScore W4383109031C2777042112 @default.
- W4383109031 hasConceptScore W4383109031C31972630 @default.
- W4383109031 hasConceptScore W4383109031C33923547 @default.
- W4383109031 hasConceptScore W4383109031C41008148 @default.
- W4383109031 hasConceptScore W4383109031C45347329 @default.
- W4383109031 hasConceptScore W4383109031C50644808 @default.
- W4383109031 hasFunder F4320321001 @default.
- W4383109031 hasFunder F4320321885 @default.
- W4383109031 hasFunder F4320335777 @default.
- W4383109031 hasFunder F4320335787 @default.
- W4383109031 hasLocation W43831090311 @default.
- W4383109031 hasLocation W43831090312 @default.
- W4383109031 hasOpenAccess W4383109031 @default.
- W4383109031 hasPrimaryLocation W43831090311 @default.
- W4383109031 hasRelatedWork W1492949529 @default.
- W4383109031 hasRelatedWork W162062087 @default.
- W4383109031 hasRelatedWork W1989965977 @default.
- W4383109031 hasRelatedWork W2026226327 @default.
- W4383109031 hasRelatedWork W2056095867 @default.
- W4383109031 hasRelatedWork W2085032340 @default.
- W4383109031 hasRelatedWork W2181452467 @default.
- W4383109031 hasRelatedWork W2232767080 @default.
- W4383109031 hasRelatedWork W2373997809 @default.
- W4383109031 hasRelatedWork W3039499377 @default.
- W4383109031 isParatext "false" @default.
- W4383109031 isRetracted "false" @default.
- W4383109031 workType "article" @default.