Matches in SemOpenAlex for { <https://semopenalex.org/work/W2963554441> ?p ?o ?g. }
- W2963554441 abstract "Discovering 3D arrangements of objects from single indoor images is important given its many applications such as interior design and content creation for virtual environments. Although heavily researched in the recent years, existing approaches break down under medium to heavy occlusion as the core image-space region detection module fails in absence of directly visible cues. Instead, we take into account holistic contextual 3D information, exploiting the fact that objects in indoor scenes co-occur mostly in typical configurations. First, we use a neural network trained on real indoor annotated images to extract 2D keypoints, and feed them to a 3D candidate object generation stage. Then, we solve a global selection problem among these candidates using pairwise co-occurrence statistics discovered from a large 3D scene database. We iterate the process allowing for candidates with low keypoint response to be incrementally detected based on the location of the already discovered nearby objects. We demonstrate significant performance improvement over combinations of state-of-the-art methods, especially for scenes with moderately to severely occluded objects." @default.
- W2963554441 created "2019-07-30" @default.
- W2963554441 creator A5005113126 @default.
- W2963554441 creator A5021074890 @default.
- W2963554441 creator A5028817790 @default.
- W2963554441 creator A5052779906 @default.
- W2963554441 creator A5058170430 @default.
- W2963554441 creator A5086977582 @default.
- W2963554441 date "2018-09-01" @default.
- W2963554441 modified "2023-09-22" @default.
- W2963554441 title "SeeThrough: Finding Objects in Heavily Occluded Indoor Scene Images" @default.
- W2963554441 cites W1509835260 @default.
- W2963554441 cites W1585614163 @default.
- W2963554441 cites W1949483711 @default.
- W2963554441 cites W1987266124 @default.
- W2963554441 cites W1990345222 @default.
- W2963554441 cites W1990884907 @default.
- W2963554441 cites W2010625607 @default.
- W2963554441 cites W2011511325 @default.
- W2963554441 cites W2021261909 @default.
- W2963554441 cites W2028541416 @default.
- W2963554441 cites W2060268527 @default.
- W2963554441 cites W2071634722 @default.
- W2963554441 cites W2092399515 @default.
- W2963554441 cites W2113107168 @default.
- W2963554441 cites W2118824402 @default.
- W2963554441 cites W2126836862 @default.
- W2963554441 cites W2157953764 @default.
- W2963554441 cites W2161969291 @default.
- W2963554441 cites W2162559028 @default.
- W2963554441 cites W2162950292 @default.
- W2963554441 cites W2189149359 @default.
- W2963554441 cites W2190691619 @default.
- W2963554441 cites W2194775991 @default.
- W2963554441 cites W2199215860 @default.
- W2963554441 cites W2439650069 @default.
- W2963554441 cites W2519379752 @default.
- W2963554441 cites W2534523274 @default.
- W2963554441 cites W2563100679 @default.
- W2963554441 cites W2575575053 @default.
- W2963554441 cites W2613718673 @default.
- W2963554441 cites W2756353073 @default.
- W2963554441 cites W2962809185 @default.
- W2963554441 cites W2964304707 @default.
- W2963554441 cites W3106165820 @default.
- W2963554441 cites W566730006 @default.
- W2963554441 doi "https://doi.org/10.1109/3dv.2018.00039" @default.
- W2963554441 hasPublicationYear "2018" @default.
- W2963554441 type Work @default.
- W2963554441 sameAs 2963554441 @default.
- W2963554441 citedByCount "8" @default.
- W2963554441 countsByYear W29635544412018 @default.
- W2963554441 countsByYear W29635544412019 @default.
- W2963554441 countsByYear W29635544412020 @default.
- W2963554441 countsByYear W29635544412021 @default.
- W2963554441 crossrefType "proceedings-article" @default.
- W2963554441 hasAuthorship W2963554441A5005113126 @default.
- W2963554441 hasAuthorship W2963554441A5021074890 @default.
- W2963554441 hasAuthorship W2963554441A5028817790 @default.
- W2963554441 hasAuthorship W2963554441A5052779906 @default.
- W2963554441 hasAuthorship W2963554441A5058170430 @default.
- W2963554441 hasAuthorship W2963554441A5086977582 @default.
- W2963554441 hasBestOaLocation W29635544412 @default.
- W2963554441 hasConcept C111919701 @default.
- W2963554441 hasConcept C115961682 @default.
- W2963554441 hasConcept C153180895 @default.
- W2963554441 hasConcept C154945302 @default.
- W2963554441 hasConcept C184898388 @default.
- W2963554441 hasConcept C2776151529 @default.
- W2963554441 hasConcept C2781238097 @default.
- W2963554441 hasConcept C31972630 @default.
- W2963554441 hasConcept C41008148 @default.
- W2963554441 hasConcept C98045186 @default.
- W2963554441 hasConceptScore W2963554441C111919701 @default.
- W2963554441 hasConceptScore W2963554441C115961682 @default.
- W2963554441 hasConceptScore W2963554441C153180895 @default.
- W2963554441 hasConceptScore W2963554441C154945302 @default.
- W2963554441 hasConceptScore W2963554441C184898388 @default.
- W2963554441 hasConceptScore W2963554441C2776151529 @default.
- W2963554441 hasConceptScore W2963554441C2781238097 @default.
- W2963554441 hasConceptScore W2963554441C31972630 @default.
- W2963554441 hasConceptScore W2963554441C41008148 @default.
- W2963554441 hasConceptScore W2963554441C98045186 @default.
- W2963554441 hasLocation W29635544411 @default.
- W2963554441 hasLocation W29635544412 @default.
- W2963554441 hasLocation W29635544413 @default.
- W2963554441 hasOpenAccess W2963554441 @default.
- W2963554441 hasPrimaryLocation W29635544411 @default.
- W2963554441 hasRelatedWork W125693051 @default.
- W2963554441 hasRelatedWork W1861492603 @default.
- W2963554441 hasRelatedWork W1923184257 @default.
- W2963554441 hasRelatedWork W2010625607 @default.
- W2963554441 hasRelatedWork W2077263423 @default.
- W2963554441 hasRelatedWork W2174266739 @default.
- W2963554441 hasRelatedWork W2194775991 @default.
- W2963554441 hasRelatedWork W2534523274 @default.
- W2963554441 hasRelatedWork W2595059465 @default.
- W2963554441 hasRelatedWork W2765423304 @default.
- W2963554441 hasRelatedWork W2885364117 @default.
- W2963554441 hasRelatedWork W2897807930 @default.