Matches in SemOpenAlex for { <https://semopenalex.org/work/W2972916125> ?p ?o ?g. }
- W2972916125 abstract "A key challenge for RGB-D segmentation is how to effectively incorporate 3D geometric information from the depth channel into 2D appearance features. We propose to model the effective receptive field of 2D convolution based on the scale and locality from the 3D neighborhood. Standard convolutions are local in the image space ($u, v$), often with a fixed receptive field of 3x3 pixels. We propose to define convolutions local with respect to the corresponding point in the 3D real-world space ($x, y, z$), where the depth channel is used to adapt the receptive field of the convolution, which yields the resulting filters invariant to scale and focusing on the certain range of depth. We introduce 3D Neighborhood Convolution (3DN-Conv), a convolutional operator around 3D neighborhoods. Further, we can use estimated depth to use our RGB-D based semantic segmentation model from RGB input. Experimental results validate that our proposed 3DN-Conv operator improves semantic segmentation, using either ground-truth depth (RGB-D) or estimated depth (RGB)." @default.
- W2972916125 created "2019-09-19" @default.
- W2972916125 creator A5002625178 @default.
- W2972916125 creator A5053359186 @default.
- W2972916125 creator A5056112540 @default.
- W2972916125 date "2019-10-03" @default.
- W2972916125 modified "2023-10-17" @default.
- W2972916125 title "3D Neighborhood Convolution: Learning Depth-Aware Features for RGB-D and RGB Semantic Segmentation" @default.
- W2972916125 cites W125693051 @default.
- W2972916125 cites W1565402342 @default.
- W2972916125 cites W1903029394 @default.
- W2972916125 cites W2067912884 @default.
- W2972916125 cites W2115579991 @default.
- W2972916125 cites W2132947399 @default.
- W2972916125 cites W2158211626 @default.
- W2972916125 cites W2158572399 @default.
- W2972916125 cites W2171740948 @default.
- W2972916125 cites W2190691619 @default.
- W2972916125 cites W2414711238 @default.
- W2972916125 cites W2507296351 @default.
- W2972916125 cites W2556967412 @default.
- W2972916125 cites W2557465155 @default.
- W2972916125 cites W2560023338 @default.
- W2972916125 cites W2560609797 @default.
- W2972916125 cites W2563705555 @default.
- W2972916125 cites W2587989515 @default.
- W2972916125 cites W2601564443 @default.
- W2972916125 cites W2605938684 @default.
- W2972916125 cites W2630837129 @default.
- W2972916125 cites W2772619632 @default.
- W2972916125 cites W2776622059 @default.
- W2972916125 cites W2798872691 @default.
- W2972916125 cites W2799166040 @default.
- W2972916125 cites W2889469641 @default.
- W2972916125 cites W2951713345 @default.
- W2972916125 cites W2962807621 @default.
- W2972916125 cites W2963091558 @default.
- W2972916125 cites W2963121255 @default.
- W2972916125 cites W2963420686 @default.
- W2972916125 cites W2963488291 @default.
- W2972916125 cites W2963591054 @default.
- W2972916125 cites W2963881378 @default.
- W2972916125 cites W2963896186 @default.
- W2972916125 cites W2963911235 @default.
- W2972916125 cites W2966926453 @default.
- W2972916125 cites W2979596232 @default.
- W2972916125 doi "https://doi.org/10.48550/arxiv.1910.01460" @default.
- W2972916125 hasPublicationYear "2019" @default.
- W2972916125 type Work @default.
- W2972916125 sameAs 2972916125 @default.
- W2972916125 citedByCount "0" @default.
- W2972916125 crossrefType "posted-content" @default.
- W2972916125 hasAuthorship W2972916125A5002625178 @default.
- W2972916125 hasAuthorship W2972916125A5053359186 @default.
- W2972916125 hasAuthorship W2972916125A5056112540 @default.
- W2972916125 hasBestOaLocation W29729161251 @default.
- W2972916125 hasConcept C127162648 @default.
- W2972916125 hasConcept C146849305 @default.
- W2972916125 hasConcept C153180895 @default.
- W2972916125 hasConcept C154945302 @default.
- W2972916125 hasConcept C190470478 @default.
- W2972916125 hasConcept C31258907 @default.
- W2972916125 hasConcept C31972630 @default.
- W2972916125 hasConcept C33923547 @default.
- W2972916125 hasConcept C37914503 @default.
- W2972916125 hasConcept C41008148 @default.
- W2972916125 hasConcept C45347329 @default.
- W2972916125 hasConcept C50644808 @default.
- W2972916125 hasConcept C82990744 @default.
- W2972916125 hasConcept C89600930 @default.
- W2972916125 hasConceptScore W2972916125C127162648 @default.
- W2972916125 hasConceptScore W2972916125C146849305 @default.
- W2972916125 hasConceptScore W2972916125C153180895 @default.
- W2972916125 hasConceptScore W2972916125C154945302 @default.
- W2972916125 hasConceptScore W2972916125C190470478 @default.
- W2972916125 hasConceptScore W2972916125C31258907 @default.
- W2972916125 hasConceptScore W2972916125C31972630 @default.
- W2972916125 hasConceptScore W2972916125C33923547 @default.
- W2972916125 hasConceptScore W2972916125C37914503 @default.
- W2972916125 hasConceptScore W2972916125C41008148 @default.
- W2972916125 hasConceptScore W2972916125C45347329 @default.
- W2972916125 hasConceptScore W2972916125C50644808 @default.
- W2972916125 hasConceptScore W2972916125C82990744 @default.
- W2972916125 hasConceptScore W2972916125C89600930 @default.
- W2972916125 hasLocation W29729161251 @default.
- W2972916125 hasOpenAccess W2972916125 @default.
- W2972916125 hasPrimaryLocation W29729161251 @default.
- W2972916125 hasRelatedWork W144883078 @default.
- W2972916125 hasRelatedWork W2030712947 @default.
- W2972916125 hasRelatedWork W2063808656 @default.
- W2972916125 hasRelatedWork W2111610923 @default.
- W2972916125 hasRelatedWork W2134924024 @default.
- W2972916125 hasRelatedWork W2157822554 @default.
- W2972916125 hasRelatedWork W2460208817 @default.
- W2972916125 hasRelatedWork W2558375057 @default.
- W2972916125 hasRelatedWork W2739874619 @default.
- W2972916125 hasRelatedWork W3004045746 @default.
- W2972916125 isParatext "false" @default.
- W2972916125 isRetracted "false" @default.
- W2972916125 magId "2972916125" @default.