Matches in SemOpenAlex for { <https://semopenalex.org/work/W3134419943> ?p ?o ?g. }
- W3134419943 endingPage "3690" @default.
- W3134419943 startingPage "3676" @default.
- W3134419943 abstract "Photometric stereo recovers three-dimensional (3D) object surface normal from multiple images under different illumination directions. Traditional photometric stereo methods suffer from the problem of non-Lambertian surfaces with general reflectance. By leveraging deep neural networks, learning-based methods are capable of improving the surface normal estimation under general non-Lambertian surfaces. These state-of-the-art learning-based methods however do not associate surface normal with reconstructed images and, therefore, they cannot explore the beneficial effect of such association on the estimation of the surface normal. In this paper, we specifically exploit the positive impact of this association and propose a novel dual regression network for both fine surface normals and arbitrary reconstructed images in calibrated photometric stereo. Our work unifies the 3D reconstruction and rendering tasks in a deep learning framework, with the explorations including: 1. generating specified reconstructed images under arbitrary illumination directions, which provides more intuitive perception of the reflectance and is extremely useful for visual applications, such as virtual reality, and 2. our dual regression scheme introduces an additional constraint on observed images and reconstructed images, which forms a closed-loop to provide additional supervision. Experiments show that our proposed method achieves accurate reconstructed images under arbitrarily specified illumination directions and it significantly outperforms the state-of-the-art learning-based single regression methods in calibrated photometric stereo." @default.
- W3134419943 created "2021-03-15" @default.
- W3134419943 creator A5002319878 @default.
- W3134419943 creator A5029633264 @default.
- W3134419943 creator A5086183661 @default.
- W3134419943 date "2021-01-01" @default.
- W3134419943 modified "2023-10-17" @default.
- W3134419943 title "Recovering Surface Normal and Arbitrary Images: A Dual Regression Network for Photometric Stereo" @default.
- W3134419943 cites W1566485861 @default.
- W3134419943 cites W1969520253 @default.
- W3134419943 cites W1974830217 @default.
- W3134419943 cites W1975089519 @default.
- W3134419943 cites W1975931458 @default.
- W3134419943 cites W1978356057 @default.
- W3134419943 cites W2076130323 @default.
- W3134419943 cites W2085608034 @default.
- W3134419943 cites W2097839898 @default.
- W3134419943 cites W2112417771 @default.
- W3134419943 cites W2121649761 @default.
- W3134419943 cites W2133665775 @default.
- W3134419943 cites W2134019950 @default.
- W3134419943 cites W2143979639 @default.
- W3134419943 cites W2151159838 @default.
- W3134419943 cites W2158018118 @default.
- W3134419943 cites W2161810906 @default.
- W3134419943 cites W2162137382 @default.
- W3134419943 cites W2165192967 @default.
- W3134419943 cites W2194775991 @default.
- W3134419943 cites W2254591945 @default.
- W3134419943 cites W2736951491 @default.
- W3134419943 cites W2766067961 @default.
- W3134419943 cites W2776016831 @default.
- W3134419943 cites W2787460109 @default.
- W3134419943 cites W2884608015 @default.
- W3134419943 cites W2889383273 @default.
- W3134419943 cites W2905957315 @default.
- W3134419943 cites W2922144044 @default.
- W3134419943 cites W2948619611 @default.
- W3134419943 cites W2954058873 @default.
- W3134419943 cites W2961702176 @default.
- W3134419943 cites W2962793481 @default.
- W3134419943 cites W2963002018 @default.
- W3134419943 cites W2963444790 @default.
- W3134419943 cites W2964094607 @default.
- W3134419943 cites W2982863468 @default.
- W3134419943 cites W2990635811 @default.
- W3134419943 cites W3005895305 @default.
- W3134419943 cites W3035523051 @default.
- W3134419943 cites W3039644234 @default.
- W3134419943 cites W3151597212 @default.
- W3134419943 doi "https://doi.org/10.1109/tip.2021.3064230" @default.
- W3134419943 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/33705315" @default.
- W3134419943 hasPublicationYear "2021" @default.
- W3134419943 type Work @default.
- W3134419943 sameAs 3134419943 @default.
- W3134419943 citedByCount "25" @default.
- W3134419943 countsByYear W31344199432021 @default.
- W3134419943 countsByYear W31344199432022 @default.
- W3134419943 countsByYear W31344199432023 @default.
- W3134419943 crossrefType "journal-article" @default.
- W3134419943 hasAuthorship W3134419943A5002319878 @default.
- W3134419943 hasAuthorship W3134419943A5029633264 @default.
- W3134419943 hasAuthorship W3134419943A5086183661 @default.
- W3134419943 hasBestOaLocation W31344199432 @default.
- W3134419943 hasConcept C108583219 @default.
- W3134419943 hasConcept C115961682 @default.
- W3134419943 hasConcept C118732077 @default.
- W3134419943 hasConcept C153180895 @default.
- W3134419943 hasConcept C154945302 @default.
- W3134419943 hasConcept C205711294 @default.
- W3134419943 hasConcept C2524010 @default.
- W3134419943 hasConcept C2776799497 @default.
- W3134419943 hasConcept C31972630 @default.
- W3134419943 hasConcept C33923547 @default.
- W3134419943 hasConcept C41008148 @default.
- W3134419943 hasConcept C44365914 @default.
- W3134419943 hasConcept C50644808 @default.
- W3134419943 hasConceptScore W3134419943C108583219 @default.
- W3134419943 hasConceptScore W3134419943C115961682 @default.
- W3134419943 hasConceptScore W3134419943C118732077 @default.
- W3134419943 hasConceptScore W3134419943C153180895 @default.
- W3134419943 hasConceptScore W3134419943C154945302 @default.
- W3134419943 hasConceptScore W3134419943C205711294 @default.
- W3134419943 hasConceptScore W3134419943C2524010 @default.
- W3134419943 hasConceptScore W3134419943C2776799497 @default.
- W3134419943 hasConceptScore W3134419943C31972630 @default.
- W3134419943 hasConceptScore W3134419943C33923547 @default.
- W3134419943 hasConceptScore W3134419943C41008148 @default.
- W3134419943 hasConceptScore W3134419943C44365914 @default.
- W3134419943 hasConceptScore W3134419943C50644808 @default.
- W3134419943 hasFunder F4320321001 @default.
- W3134419943 hasFunder F4320335765 @default.
- W3134419943 hasFunder F4320335830 @default.
- W3134419943 hasLocation W31344199431 @default.
- W3134419943 hasLocation W31344199432 @default.
- W3134419943 hasOpenAccess W3134419943 @default.
- W3134419943 hasPrimaryLocation W31344199431 @default.
- W3134419943 hasRelatedWork W1503414886 @default.