Matches in SemOpenAlex for { <https://semopenalex.org/work/W4225522995> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W4225522995 abstract "The problem of estimating a surface shape from its observed reflectance properties still remains a challenging task in computer vision. The presence of global illumination effects such as inter-reflections or cast shadows makes the task particularly difficult for non-convex real-world surfaces. State-of-the-art methods for calibrated photometric stereo address these issues using convolutional neural networks (CNNs) that primarily aim to capture either the spatial context among adjacent pixels or the photometric one formed by illuminating a sample from adjacent directions.In this paper, we bridge these two objectives and introduce an efficient fully-convolutional architecture that can leverage both spatial and photometric context simultaneously. In contrast to existing approaches that rely on standard 2D CNNs and regress directly to surface normals, we argue that using separable 4D convolutions and regressing to 2D Gaussian heat-maps severely reduces the size of the network and leads to more stable predictions.Our experimental results on a real-world photometric stereo benchmark show that the proposed approach outperforms the existing published methods in accuracy. The source code for our method is available at https://github.com/DawyD/UNet-PS-4D." @default.
- W4225522995 created "2022-05-05" @default.
- W4225522995 creator A5037267640 @default.
- W4225522995 creator A5038674741 @default.
- W4225522995 creator A5057420317 @default.
- W4225522995 creator A5087632602 @default.
- W4225522995 date "2021-12-01" @default.
- W4225522995 modified "2023-10-04" @default.
- W4225522995 title "Leveraging Spatial and Photometric Context for Calibrated Non-Lambertian Photometric Stereo" @default.
- W4225522995 cites W1969520253 @default.
- W4225522995 cites W1975089519 @default.
- W4225522995 cites W1978356057 @default.
- W4225522995 cites W2021398211 @default.
- W4225522995 cites W2165192967 @default.
- W4225522995 cites W2474450142 @default.
- W4225522995 cites W2766067961 @default.
- W4225522995 cites W2884608015 @default.
- W4225522995 cites W2889383273 @default.
- W4225522995 cites W2948619611 @default.
- W4225522995 cites W2990635811 @default.
- W4225522995 cites W3034637632 @default.
- W4225522995 cites W3035687035 @default.
- W4225522995 cites W3039644234 @default.
- W4225522995 doi "https://doi.org/10.1109/3dv53792.2021.00049" @default.
- W4225522995 hasPublicationYear "2021" @default.
- W4225522995 type Work @default.
- W4225522995 citedByCount "6" @default.
- W4225522995 countsByYear W42255229952022 @default.
- W4225522995 countsByYear W42255229952023 @default.
- W4225522995 crossrefType "proceedings-article" @default.
- W4225522995 hasAuthorship W4225522995A5037267640 @default.
- W4225522995 hasAuthorship W4225522995A5038674741 @default.
- W4225522995 hasAuthorship W4225522995A5057420317 @default.
- W4225522995 hasAuthorship W4225522995A5087632602 @default.
- W4225522995 hasConcept C115961682 @default.
- W4225522995 hasConcept C151730666 @default.
- W4225522995 hasConcept C153083717 @default.
- W4225522995 hasConcept C154945302 @default.
- W4225522995 hasConcept C160633673 @default.
- W4225522995 hasConcept C185798385 @default.
- W4225522995 hasConcept C205649164 @default.
- W4225522995 hasConcept C2779343474 @default.
- W4225522995 hasConcept C31972630 @default.
- W4225522995 hasConcept C41008148 @default.
- W4225522995 hasConcept C44365914 @default.
- W4225522995 hasConcept C58640448 @default.
- W4225522995 hasConcept C64754055 @default.
- W4225522995 hasConcept C81363708 @default.
- W4225522995 hasConcept C86803240 @default.
- W4225522995 hasConceptScore W4225522995C115961682 @default.
- W4225522995 hasConceptScore W4225522995C151730666 @default.
- W4225522995 hasConceptScore W4225522995C153083717 @default.
- W4225522995 hasConceptScore W4225522995C154945302 @default.
- W4225522995 hasConceptScore W4225522995C160633673 @default.
- W4225522995 hasConceptScore W4225522995C185798385 @default.
- W4225522995 hasConceptScore W4225522995C205649164 @default.
- W4225522995 hasConceptScore W4225522995C2779343474 @default.
- W4225522995 hasConceptScore W4225522995C31972630 @default.
- W4225522995 hasConceptScore W4225522995C41008148 @default.
- W4225522995 hasConceptScore W4225522995C44365914 @default.
- W4225522995 hasConceptScore W4225522995C58640448 @default.
- W4225522995 hasConceptScore W4225522995C64754055 @default.
- W4225522995 hasConceptScore W4225522995C81363708 @default.
- W4225522995 hasConceptScore W4225522995C86803240 @default.
- W4225522995 hasLocation W42255229951 @default.
- W4225522995 hasOpenAccess W4225522995 @default.
- W4225522995 hasPrimaryLocation W42255229951 @default.
- W4225522995 hasRelatedWork W121273120 @default.
- W4225522995 hasRelatedWork W1554604122 @default.
- W4225522995 hasRelatedWork W2002009170 @default.
- W4225522995 hasRelatedWork W2023308736 @default.
- W4225522995 hasRelatedWork W2090093270 @default.
- W4225522995 hasRelatedWork W2337415362 @default.
- W4225522995 hasRelatedWork W2740820121 @default.
- W4225522995 hasRelatedWork W2981632971 @default.
- W4225522995 hasRelatedWork W317572212 @default.
- W4225522995 hasRelatedWork W4312857205 @default.
- W4225522995 isParatext "false" @default.
- W4225522995 isRetracted "false" @default.
- W4225522995 workType "article" @default.