Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387092538> ?p ?o ?g. }
- W4387092538 endingPage "7494" @default.
- W4387092538 startingPage "7487" @default.
- W4387092538 abstract "Scene understanding is crucial for autonomous systems to reliably navigate in the real world. Panoptic segmentation of 3D LiDAR scans allows us to semantically describe a vehicle's environment by predicting semantic classes for each 3D point and to identify individual instances through different instance IDs. To describe the dynamics of the surroundings, 4D panoptic segmentation further extends this information with temporarily consistent instance IDs to identify the different instances in the scans consistently over whole sequences. Previous approaches for 4D panoptic segmentation rely on post-processing steps and are often not end-to-end trainable. In this paper, we propose a novel approach that can be trained end-to-end and directly predicts a set of non-overlapping masks along with their semantic classes and instance IDs that are consistent over time without any post-processing like clustering or associations between predictions. We extend a mask-based 3D panoptic segmentation model to 4D by reusing queries that decoded instances in previous scans. This way, each query decodes the same instance over time, carries its ID and the tracking is performed implicitly. This enables us to jointly optimize segmentation and tracking and directly supervise for 4D panoptic segmentation." @default.
- W4387092538 created "2023-09-28" @default.
- W4387092538 creator A5004673510 @default.
- W4387092538 creator A5010951584 @default.
- W4387092538 creator A5011166267 @default.
- W4387092538 creator A5012654952 @default.
- W4387092538 creator A5040103218 @default.
- W4387092538 creator A5068364473 @default.
- W4387092538 date "2023-11-01" @default.
- W4387092538 modified "2023-10-09" @default.
- W4387092538 title "Mask4D: End-to-End Mask-Based 4D Panoptic Segmentation for LiDAR Sequences" @default.
- W4387092538 cites W2150066425 @default.
- W4387092538 cites W2805521962 @default.
- W4387092538 cites W2897529137 @default.
- W4387092538 cites W2963125977 @default.
- W4387092538 cites W2963182550 @default.
- W4387092538 cites W2968296999 @default.
- W4387092538 cites W2990613095 @default.
- W4387092538 cites W2991216808 @default.
- W4387092538 cites W2999219213 @default.
- W4387092538 cites W3003437478 @default.
- W4387092538 cites W3012494314 @default.
- W4387092538 cites W3080432947 @default.
- W4387092538 cites W3096609285 @default.
- W4387092538 cites W3109154950 @default.
- W4387092538 cites W3119686997 @default.
- W4387092538 cites W3129377622 @default.
- W4387092538 cites W3132607695 @default.
- W4387092538 cites W3152786524 @default.
- W4387092538 cites W3167095230 @default.
- W4387092538 cites W3168649818 @default.
- W4387092538 cites W3168659596 @default.
- W4387092538 cites W3174527233 @default.
- W4387092538 cites W3177330511 @default.
- W4387092538 cites W3197472509 @default.
- W4387092538 cites W3203974803 @default.
- W4387092538 cites W4205588343 @default.
- W4387092538 cites W4312473433 @default.
- W4387092538 cites W4312815172 @default.
- W4387092538 cites W4312850715 @default.
- W4387092538 cites W4315783786 @default.
- W4387092538 cites W4320737012 @default.
- W4387092538 cites W4386071758 @default.
- W4387092538 doi "https://doi.org/10.1109/lra.2023.3320020" @default.
- W4387092538 hasPublicationYear "2023" @default.
- W4387092538 type Work @default.
- W4387092538 citedByCount "0" @default.
- W4387092538 crossrefType "journal-article" @default.
- W4387092538 hasAuthorship W4387092538A5004673510 @default.
- W4387092538 hasAuthorship W4387092538A5010951584 @default.
- W4387092538 hasAuthorship W4387092538A5011166267 @default.
- W4387092538 hasAuthorship W4387092538A5012654952 @default.
- W4387092538 hasAuthorship W4387092538A5040103218 @default.
- W4387092538 hasAuthorship W4387092538A5068364473 @default.
- W4387092538 hasConcept C11413529 @default.
- W4387092538 hasConcept C138569888 @default.
- W4387092538 hasConcept C153180895 @default.
- W4387092538 hasConcept C154945302 @default.
- W4387092538 hasConcept C177264268 @default.
- W4387092538 hasConcept C17744445 @default.
- W4387092538 hasConcept C199360897 @default.
- W4387092538 hasConcept C199539241 @default.
- W4387092538 hasConcept C2524010 @default.
- W4387092538 hasConcept C2778858076 @default.
- W4387092538 hasConcept C28719098 @default.
- W4387092538 hasConcept C31972630 @default.
- W4387092538 hasConcept C33923547 @default.
- W4387092538 hasConcept C41008148 @default.
- W4387092538 hasConcept C57273362 @default.
- W4387092538 hasConcept C73555534 @default.
- W4387092538 hasConcept C89600930 @default.
- W4387092538 hasConcept C94625758 @default.
- W4387092538 hasConceptScore W4387092538C11413529 @default.
- W4387092538 hasConceptScore W4387092538C138569888 @default.
- W4387092538 hasConceptScore W4387092538C153180895 @default.
- W4387092538 hasConceptScore W4387092538C154945302 @default.
- W4387092538 hasConceptScore W4387092538C177264268 @default.
- W4387092538 hasConceptScore W4387092538C17744445 @default.
- W4387092538 hasConceptScore W4387092538C199360897 @default.
- W4387092538 hasConceptScore W4387092538C199539241 @default.
- W4387092538 hasConceptScore W4387092538C2524010 @default.
- W4387092538 hasConceptScore W4387092538C2778858076 @default.
- W4387092538 hasConceptScore W4387092538C28719098 @default.
- W4387092538 hasConceptScore W4387092538C31972630 @default.
- W4387092538 hasConceptScore W4387092538C33923547 @default.
- W4387092538 hasConceptScore W4387092538C41008148 @default.
- W4387092538 hasConceptScore W4387092538C57273362 @default.
- W4387092538 hasConceptScore W4387092538C73555534 @default.
- W4387092538 hasConceptScore W4387092538C89600930 @default.
- W4387092538 hasConceptScore W4387092538C94625758 @default.
- W4387092538 hasIssue "11" @default.
- W4387092538 hasLocation W43870925381 @default.
- W4387092538 hasOpenAccess W4387092538 @default.
- W4387092538 hasPrimaryLocation W43870925381 @default.
- W4387092538 hasRelatedWork W1710116222 @default.
- W4387092538 hasRelatedWork W2197002326 @default.
- W4387092538 hasRelatedWork W2345320341 @default.
- W4387092538 hasRelatedWork W2494728058 @default.