Matches in SemOpenAlex for { <https://semopenalex.org/work/W3137459498> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W3137459498 abstract "We explore how a general AI algorithm can be used for 3D scene understanding to reduce the need for training data. More exactly, we propose a modification of the Monte Carlo Tree Search (MCTS) algorithm to retrieve objects and room layouts from noisy RGB-D scans. While MCTS was developed as a game-playing algorithm, we show it can also be used for complex perception problems. Our adapted MCTS algorithm has few easy-to-tune hyperparameters and can optimise general losses. We use it to optimise the posterior probability of objects and room layout hypotheses given the RGB-D data. This results in an analysis-by-synthesis approach that explores the solution space by rendering the current solution and comparing it to the RGB-D observations. To perform this exploration even more efficiently, we propose simple changes to the standard MCTS' tree construction and exploration policy. We demonstrate our approach on the ScanNet dataset. Our method often retrieves configurations that are better than some manual annotations, especially on layouts." @default.
- W3137459498 created "2021-03-29" @default.
- W3137459498 creator A5014583447 @default.
- W3137459498 creator A5042153947 @default.
- W3137459498 creator A5049441604 @default.
- W3137459498 creator A5054501788 @default.
- W3137459498 creator A5068079834 @default.
- W3137459498 creator A5070382607 @default.
- W3137459498 date "2021-06-20" @default.
- W3137459498 modified "2023-10-06" @default.
- W3137459498 title "Monte Carlo Scene Search for 3D Scene Understanding" @default.
- W3137459498 cites W1714211023 @default.
- W3137459498 cites W1962921203 @default.
- W3137459498 cites W1969778848 @default.
- W3137459498 cites W2023574675 @default.
- W3137459498 cites W2068397385 @default.
- W3137459498 cites W2092399515 @default.
- W3137459498 cites W2152571752 @default.
- W3137459498 cites W2190691619 @default.
- W3137459498 cites W2201056710 @default.
- W3137459498 cites W2534523274 @default.
- W3137459498 cites W2594519801 @default.
- W3137459498 cites W2772518193 @default.
- W3137459498 cites W2775610217 @default.
- W3137459498 cites W2776645264 @default.
- W3137459498 cites W2794800539 @default.
- W3137459498 cites W2903435684 @default.
- W3137459498 cites W2908617908 @default.
- W3137459498 cites W2949768986 @default.
- W3137459498 cites W2963121255 @default.
- W3137459498 cites W2963125977 @default.
- W3137459498 cites W2964062501 @default.
- W3137459498 cites W2964076802 @default.
- W3137459498 cites W2965084509 @default.
- W3137459498 cites W2988715931 @default.
- W3137459498 cites W3003352491 @default.
- W3137459498 cites W3012008866 @default.
- W3137459498 cites W3035424742 @default.
- W3137459498 cites W3044589935 @default.
- W3137459498 cites W3047878062 @default.
- W3137459498 cites W3049552940 @default.
- W3137459498 cites W3097660860 @default.
- W3137459498 cites W3108800063 @default.
- W3137459498 cites W566730006 @default.
- W3137459498 hasPublicationYear "2021" @default.
- W3137459498 type Work @default.
- W3137459498 sameAs 3137459498 @default.
- W3137459498 citedByCount "0" @default.
- W3137459498 crossrefType "proceedings-article" @default.
- W3137459498 hasAuthorship W3137459498A5014583447 @default.
- W3137459498 hasAuthorship W3137459498A5042153947 @default.
- W3137459498 hasAuthorship W3137459498A5049441604 @default.
- W3137459498 hasAuthorship W3137459498A5054501788 @default.
- W3137459498 hasAuthorship W3137459498A5068079834 @default.
- W3137459498 hasAuthorship W3137459498A5070382607 @default.
- W3137459498 hasBestOaLocation W31374594981 @default.
- W3137459498 hasConcept C105795698 @default.
- W3137459498 hasConcept C121684516 @default.
- W3137459498 hasConcept C154945302 @default.
- W3137459498 hasConcept C19499675 @default.
- W3137459498 hasConcept C31972630 @default.
- W3137459498 hasConcept C33923547 @default.
- W3137459498 hasConcept C41008148 @default.
- W3137459498 hasConceptScore W3137459498C105795698 @default.
- W3137459498 hasConceptScore W3137459498C121684516 @default.
- W3137459498 hasConceptScore W3137459498C154945302 @default.
- W3137459498 hasConceptScore W3137459498C19499675 @default.
- W3137459498 hasConceptScore W3137459498C31972630 @default.
- W3137459498 hasConceptScore W3137459498C33923547 @default.
- W3137459498 hasConceptScore W3137459498C41008148 @default.
- W3137459498 hasLocation W31374594981 @default.
- W3137459498 hasLocation W31374594982 @default.
- W3137459498 hasLocation W31374594983 @default.
- W3137459498 hasLocation W31374594984 @default.
- W3137459498 hasOpenAccess W3137459498 @default.
- W3137459498 hasPrimaryLocation W31374594981 @default.
- W3137459498 hasRelatedWork W1891287906 @default.
- W3137459498 hasRelatedWork W1969923398 @default.
- W3137459498 hasRelatedWork W2036807459 @default.
- W3137459498 hasRelatedWork W2058170566 @default.
- W3137459498 hasRelatedWork W2166024367 @default.
- W3137459498 hasRelatedWork W2229312674 @default.
- W3137459498 hasRelatedWork W2755342338 @default.
- W3137459498 hasRelatedWork W2772917594 @default.
- W3137459498 hasRelatedWork W2775347418 @default.
- W3137459498 hasRelatedWork W3116076068 @default.
- W3137459498 isParatext "false" @default.
- W3137459498 isRetracted "false" @default.
- W3137459498 magId "3137459498" @default.
- W3137459498 workType "article" @default.