Matches in SemOpenAlex for { <https://semopenalex.org/work/W3172729300> ?p ?o ?g. }
- W3172729300 endingPage "423" @default.
- W3172729300 startingPage "413" @default.
- W3172729300 abstract "Abstract Optimal viewpoint prediction is an essential task in many computer graphics applications. Unfortunately, common viewpoint qualities suffer from two major drawbacks: dependency on clean surface meshes, which are not always available, and the lack of closed‐form expressions, which requires a costly search involving rendering. To overcome these limitations we propose to separate viewpoint selection from rendering through an end‐to‐end learning approach, whereby we reduce the influence of the mesh quality by predicting viewpoints from unstructured point clouds instead of polygonal meshes. While this makes our approach insensitive to the mesh discretization during evaluation, it only becomes possible when resolving label ambiguities that arise in this context. Therefore, we additionally propose to incorporate the label generation into the training procedure, making the label decision adaptive to the current network predictions. We show how our proposed approach allows for learning viewpoint predictions for models from different object categories and for different viewpoint qualities. Additionally, we show that prediction times are reduced from several minutes to a fraction of a second, as compared to state‐of‐the‐art (SOTA) viewpoint quality evaluation. Code and training data is available at https://github.com/schellmi42/viewpoint_learning , which is to our knowledge the biggest viewpoint quality dataset available." @default.
- W3172729300 created "2021-06-22" @default.
- W3172729300 creator A5002141920 @default.
- W3172729300 creator A5055090110 @default.
- W3172729300 creator A5061059879 @default.
- W3172729300 creator A5088394147 @default.
- W3172729300 date "2021-05-01" @default.
- W3172729300 modified "2023-10-01" @default.
- W3172729300 title "Enabling Viewpoint Learning through Dynamic Label Generation" @default.
- W3172729300 cites W2002357891 @default.
- W3172729300 cites W2008870296 @default.
- W3172729300 cites W2018995617 @default.
- W3172729300 cites W2020327719 @default.
- W3172729300 cites W2025653905 @default.
- W3172729300 cites W2031335414 @default.
- W3172729300 cites W2031367292 @default.
- W3172729300 cites W2033734529 @default.
- W3172729300 cites W2051448670 @default.
- W3172729300 cites W2079745210 @default.
- W3172729300 cites W2080145017 @default.
- W3172729300 cites W2097117768 @default.
- W3172729300 cites W2115026549 @default.
- W3172729300 cites W2137521827 @default.
- W3172729300 cites W2150884987 @default.
- W3172729300 cites W2154503164 @default.
- W3172729300 cites W2194775991 @default.
- W3172729300 cites W2295382923 @default.
- W3172729300 cites W2298482684 @default.
- W3172729300 cites W2462813209 @default.
- W3172729300 cites W2553156677 @default.
- W3172729300 cites W2557519264 @default.
- W3172729300 cites W2563408008 @default.
- W3172729300 cites W2588877877 @default.
- W3172729300 cites W2594864504 @default.
- W3172729300 cites W2604853917 @default.
- W3172729300 cites W2773910505 @default.
- W3172729300 cites W2803694688 @default.
- W3172729300 cites W2963408523 @default.
- W3172729300 cites W2964201198 @default.
- W3172729300 cites W2972765376 @default.
- W3172729300 cites W2986023562 @default.
- W3172729300 cites W3035444404 @default.
- W3172729300 cites W3122633743 @default.
- W3172729300 cites W3146719728 @default.
- W3172729300 cites W334719179 @default.
- W3172729300 cites W4237453232 @default.
- W3172729300 cites W99046655 @default.
- W3172729300 cites W1965174340 @default.
- W3172729300 doi "https://doi.org/10.1111/cgf.142643" @default.
- W3172729300 hasPublicationYear "2021" @default.
- W3172729300 type Work @default.
- W3172729300 sameAs 3172729300 @default.
- W3172729300 citedByCount "1" @default.
- W3172729300 countsByYear W31727293002022 @default.
- W3172729300 crossrefType "journal-article" @default.
- W3172729300 hasAuthorship W3172729300A5002141920 @default.
- W3172729300 hasAuthorship W3172729300A5055090110 @default.
- W3172729300 hasAuthorship W3172729300A5061059879 @default.
- W3172729300 hasAuthorship W3172729300A5088394147 @default.
- W3172729300 hasBestOaLocation W31727293001 @default.
- W3172729300 hasConcept C119857082 @default.
- W3172729300 hasConcept C121684516 @default.
- W3172729300 hasConcept C134306372 @default.
- W3172729300 hasConcept C154945302 @default.
- W3172729300 hasConcept C205711294 @default.
- W3172729300 hasConcept C31487907 @default.
- W3172729300 hasConcept C33923547 @default.
- W3172729300 hasConcept C41008148 @default.
- W3172729300 hasConcept C73000952 @default.
- W3172729300 hasConcept C77660652 @default.
- W3172729300 hasConceptScore W3172729300C119857082 @default.
- W3172729300 hasConceptScore W3172729300C121684516 @default.
- W3172729300 hasConceptScore W3172729300C134306372 @default.
- W3172729300 hasConceptScore W3172729300C154945302 @default.
- W3172729300 hasConceptScore W3172729300C205711294 @default.
- W3172729300 hasConceptScore W3172729300C31487907 @default.
- W3172729300 hasConceptScore W3172729300C33923547 @default.
- W3172729300 hasConceptScore W3172729300C41008148 @default.
- W3172729300 hasConceptScore W3172729300C73000952 @default.
- W3172729300 hasConceptScore W3172729300C77660652 @default.
- W3172729300 hasIssue "2" @default.
- W3172729300 hasLocation W31727293001 @default.
- W3172729300 hasLocation W31727293002 @default.
- W3172729300 hasLocation W31727293003 @default.
- W3172729300 hasOpenAccess W3172729300 @default.
- W3172729300 hasPrimaryLocation W31727293001 @default.
- W3172729300 hasRelatedWork W1509797150 @default.
- W3172729300 hasRelatedWork W1573437470 @default.
- W3172729300 hasRelatedWork W2001295962 @default.
- W3172729300 hasRelatedWork W2364536240 @default.
- W3172729300 hasRelatedWork W2373533945 @default.
- W3172729300 hasRelatedWork W2392654246 @default.
- W3172729300 hasRelatedWork W2541614586 @default.
- W3172729300 hasRelatedWork W3030170527 @default.
- W3172729300 hasRelatedWork W4384519882 @default.
- W3172729300 hasRelatedWork W4385489850 @default.
- W3172729300 hasVolume "40" @default.
- W3172729300 isParatext "false" @default.