Matches in SemOpenAlex for { <https://semopenalex.org/work/W3035679997> ?p ?o ?g. }
- W3035679997 abstract "Recovering the 3D shape of transparent objects using a small number of unconstrained natural images is an ill-posed problem. Complex light paths induced by refraction and reflection have prevented both traditional and deep multiview stereo from solving this challenge. We propose a physically-based network to recover 3D shape of transparent objects using a few images acquired with a mobile phone camera, under a known but arbitrary environment map. Our novel contributions include a normal representation that enables the network to model complex light transport through local computation, a rendering layer that models refractions and reflections, a cost volume specifically designed for normal refinement of transparent shapes and a feature mapping based on predicted normals for 3D point cloud reconstruction. We render a synthetic dataset to encourage the model to learn refractive light transport across different views. Our experiments show successful recovery of high-quality 3D geometry for complex transparent shapes using as few as 5-12 natural images. Code and data are publicly released." @default.
- W3035679997 created "2020-06-19" @default.
- W3035679997 creator A5046609009 @default.
- W3035679997 creator A5056145406 @default.
- W3035679997 creator A5060452999 @default.
- W3035679997 date "2020-06-01" @default.
- W3035679997 modified "2023-09-23" @default.
- W3035679997 title "Through the Looking Glass: Neural 3D Reconstruction of Transparent Shapes" @default.
- W3035679997 cites W1965581541 @default.
- W3035679997 cites W1971136783 @default.
- W3035679997 cites W197259565 @default.
- W3035679997 cites W1974830217 @default.
- W3035679997 cites W1986330187 @default.
- W3035679997 cites W1993537517 @default.
- W3035679997 cites W2001359846 @default.
- W3035679997 cites W2006082232 @default.
- W3035679997 cites W2027621340 @default.
- W3035679997 cites W2029304323 @default.
- W3035679997 cites W2049972229 @default.
- W3035679997 cites W2058056568 @default.
- W3035679997 cites W2076246983 @default.
- W3035679997 cites W2080461625 @default.
- W3035679997 cites W2093047703 @default.
- W3035679997 cites W2096942416 @default.
- W3035679997 cites W2098244689 @default.
- W3035679997 cites W2099798230 @default.
- W3035679997 cites W2111218333 @default.
- W3035679997 cites W2128084987 @default.
- W3035679997 cites W2128593740 @default.
- W3035679997 cites W2129277418 @default.
- W3035679997 cites W2137464770 @default.
- W3035679997 cites W2142147923 @default.
- W3035679997 cites W2160014001 @default.
- W3035679997 cites W2168545424 @default.
- W3035679997 cites W2207600644 @default.
- W3035679997 cites W2211820021 @default.
- W3035679997 cites W2294236821 @default.
- W3035679997 cites W2332023333 @default.
- W3035679997 cites W2467653702 @default.
- W3035679997 cites W2471962767 @default.
- W3035679997 cites W2737231059 @default.
- W3035679997 cites W2737550054 @default.
- W3035679997 cites W2738427683 @default.
- W3035679997 cites W2756342535 @default.
- W3035679997 cites W2810337759 @default.
- W3035679997 cites W2920872099 @default.
- W3035679997 cites W2958302123 @default.
- W3035679997 cites W2962909976 @default.
- W3035679997 cites W2986860185 @default.
- W3035679997 cites W3144159205 @default.
- W3035679997 cites W3164333298 @default.
- W3035679997 doi "https://doi.org/10.1109/cvpr42600.2020.00134" @default.
- W3035679997 hasPublicationYear "2020" @default.
- W3035679997 type Work @default.
- W3035679997 sameAs 3035679997 @default.
- W3035679997 citedByCount "19" @default.
- W3035679997 countsByYear W30356799972020 @default.
- W3035679997 countsByYear W30356799972021 @default.
- W3035679997 countsByYear W30356799972022 @default.
- W3035679997 countsByYear W30356799972023 @default.
- W3035679997 crossrefType "proceedings-article" @default.
- W3035679997 hasAuthorship W3035679997A5046609009 @default.
- W3035679997 hasAuthorship W3035679997A5056145406 @default.
- W3035679997 hasAuthorship W3035679997A5060452999 @default.
- W3035679997 hasBestOaLocation W30356799972 @default.
- W3035679997 hasConcept C108882727 @default.
- W3035679997 hasConcept C109950114 @default.
- W3035679997 hasConcept C11413529 @default.
- W3035679997 hasConcept C120665830 @default.
- W3035679997 hasConcept C121332964 @default.
- W3035679997 hasConcept C121684516 @default.
- W3035679997 hasConcept C131979681 @default.
- W3035679997 hasConcept C138885662 @default.
- W3035679997 hasConcept C141379421 @default.
- W3035679997 hasConcept C154945302 @default.
- W3035679997 hasConcept C17744445 @default.
- W3035679997 hasConcept C199539241 @default.
- W3035679997 hasConcept C205318122 @default.
- W3035679997 hasConcept C205711294 @default.
- W3035679997 hasConcept C20885615 @default.
- W3035679997 hasConcept C2524010 @default.
- W3035679997 hasConcept C2776359362 @default.
- W3035679997 hasConcept C2776401178 @default.
- W3035679997 hasConcept C2776799497 @default.
- W3035679997 hasConcept C31972630 @default.
- W3035679997 hasConcept C33923547 @default.
- W3035679997 hasConcept C41008148 @default.
- W3035679997 hasConcept C41895202 @default.
- W3035679997 hasConcept C45374587 @default.
- W3035679997 hasConcept C50644808 @default.
- W3035679997 hasConcept C94625758 @default.
- W3035679997 hasConceptScore W3035679997C108882727 @default.
- W3035679997 hasConceptScore W3035679997C109950114 @default.
- W3035679997 hasConceptScore W3035679997C11413529 @default.
- W3035679997 hasConceptScore W3035679997C120665830 @default.
- W3035679997 hasConceptScore W3035679997C121332964 @default.
- W3035679997 hasConceptScore W3035679997C121684516 @default.
- W3035679997 hasConceptScore W3035679997C131979681 @default.
- W3035679997 hasConceptScore W3035679997C138885662 @default.
- W3035679997 hasConceptScore W3035679997C141379421 @default.