Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386076052> ?p ?o ?g. }
- W4386076052 abstract "A central goal of visual recognition is to understand objects and scenes from a single image. 2D recognition has witnessed tremendous progress thanks to large-scale learning and general-purpose representations. Comparatively, 3D poses new challenges stemming from occlusions not depicted in the image. Prior works try to overcome these by inferring from multiple views or rely on scarce CAD models and category-specific priors which hinder scaling to novel settings. In this work, we explore single-view 3D reconstruction by learning generalizable representations inspired by advances in self-supervised learning. We introduce a simple framework that operates on 3D points of single objects or whole scenes coupled with category-agnostic large-scale training from diverse RGB-D videos. Our model, Multiview Compressive Coding (MCC), learns to compress the input appearance and geometry to predict the 3D structure by querying a 3D-aware decoder. MCC's generality and efficiency allow it to learn from large-scale and diverse data sources with strong generalization to novel objects imagined by DALLE2 or captured in-the-wild with an iPhone." @default.
- W4386076052 created "2023-08-23" @default.
- W4386076052 creator A5001594573 @default.
- W4386076052 creator A5014407395 @default.
- W4386076052 creator A5018298417 @default.
- W4386076052 creator A5023917342 @default.
- W4386076052 creator A5036069974 @default.
- W4386076052 date "2023-06-01" @default.
- W4386076052 modified "2023-09-27" @default.
- W4386076052 title "Multiview Compressive Coding for 3D Reconstruction" @default.
- W4386076052 cites W1990345222 @default.
- W4386076052 cites W2026058811 @default.
- W4386076052 cites W2028541416 @default.
- W4386076052 cites W2074954154 @default.
- W4386076052 cites W2095989672 @default.
- W4386076052 cites W2097374608 @default.
- W4386076052 cites W2104974755 @default.
- W4386076052 cites W2108598243 @default.
- W4386076052 cites W2121299550 @default.
- W4386076052 cites W2138835141 @default.
- W4386076052 cites W2148228392 @default.
- W4386076052 cites W2148916113 @default.
- W4386076052 cites W2268816372 @default.
- W4386076052 cites W2444097022 @default.
- W4386076052 cites W2471962767 @default.
- W4386076052 cites W2557465155 @default.
- W4386076052 cites W2560722161 @default.
- W4386076052 cites W2737258237 @default.
- W4386076052 cites W2799123546 @default.
- W4386076052 cites W2886499109 @default.
- W4386076052 cites W2962988048 @default.
- W4386076052 cites W2963627347 @default.
- W4386076052 cites W2963926543 @default.
- W4386076052 cites W2964137676 @default.
- W4386076052 cites W2964185501 @default.
- W4386076052 cites W2981978060 @default.
- W4386076052 cites W2983582925 @default.
- W4386076052 cites W2990578762 @default.
- W4386076052 cites W3004414671 @default.
- W4386076052 cites W3034299016 @default.
- W4386076052 cites W3034584726 @default.
- W4386076052 cites W3034968345 @default.
- W4386076052 cites W3035523051 @default.
- W4386076052 cites W3105863736 @default.
- W4386076052 cites W3107541696 @default.
- W4386076052 cites W3141954417 @default.
- W4386076052 cites W3175695459 @default.
- W4386076052 cites W3176368002 @default.
- W4386076052 cites W3203898101 @default.
- W4386076052 cites W4205172069 @default.
- W4386076052 cites W4214520160 @default.
- W4386076052 cites W4214655709 @default.
- W4386076052 cites W4312612965 @default.
- W4386076052 cites W4312969460 @default.
- W4386076052 cites W4313036632 @default.
- W4386076052 cites W4313156423 @default.
- W4386076052 cites W4313181278 @default.
- W4386076052 doi "https://doi.org/10.1109/cvpr52729.2023.00875" @default.
- W4386076052 hasPublicationYear "2023" @default.
- W4386076052 type Work @default.
- W4386076052 citedByCount "0" @default.
- W4386076052 crossrefType "proceedings-article" @default.
- W4386076052 hasAuthorship W4386076052A5001594573 @default.
- W4386076052 hasAuthorship W4386076052A5014407395 @default.
- W4386076052 hasAuthorship W4386076052A5018298417 @default.
- W4386076052 hasAuthorship W4386076052A5023917342 @default.
- W4386076052 hasAuthorship W4386076052A5036069974 @default.
- W4386076052 hasConcept C105795698 @default.
- W4386076052 hasConcept C107673813 @default.
- W4386076052 hasConcept C109950114 @default.
- W4386076052 hasConcept C119857082 @default.
- W4386076052 hasConcept C134306372 @default.
- W4386076052 hasConcept C141379421 @default.
- W4386076052 hasConcept C153180895 @default.
- W4386076052 hasConcept C154945302 @default.
- W4386076052 hasConcept C15744967 @default.
- W4386076052 hasConcept C177148314 @default.
- W4386076052 hasConcept C177769412 @default.
- W4386076052 hasConcept C179518139 @default.
- W4386076052 hasConcept C2780767217 @default.
- W4386076052 hasConcept C31972630 @default.
- W4386076052 hasConcept C33923547 @default.
- W4386076052 hasConcept C41008148 @default.
- W4386076052 hasConcept C542102704 @default.
- W4386076052 hasConcept C77637269 @default.
- W4386076052 hasConcept C82990744 @default.
- W4386076052 hasConceptScore W4386076052C105795698 @default.
- W4386076052 hasConceptScore W4386076052C107673813 @default.
- W4386076052 hasConceptScore W4386076052C109950114 @default.
- W4386076052 hasConceptScore W4386076052C119857082 @default.
- W4386076052 hasConceptScore W4386076052C134306372 @default.
- W4386076052 hasConceptScore W4386076052C141379421 @default.
- W4386076052 hasConceptScore W4386076052C153180895 @default.
- W4386076052 hasConceptScore W4386076052C154945302 @default.
- W4386076052 hasConceptScore W4386076052C15744967 @default.
- W4386076052 hasConceptScore W4386076052C177148314 @default.
- W4386076052 hasConceptScore W4386076052C177769412 @default.
- W4386076052 hasConceptScore W4386076052C179518139 @default.
- W4386076052 hasConceptScore W4386076052C2780767217 @default.
- W4386076052 hasConceptScore W4386076052C31972630 @default.