Matches in SemOpenAlex for { <https://semopenalex.org/work/W2989996808> ?p ?o ?g. }
- W2989996808 abstract "Camera and lidar are important sensor modalities for robotics in general and self-driving cars in particular. The sensors provide complementary information offering an opportunity for tight sensor-fusion. Surprisingly, lidar-only methods outperform fusion methods on the main benchmark datasets, suggesting a gap in the literature. In this work, we propose PointPainting: a sequential fusion method to fill this gap. PointPainting works by projecting lidar points into the output of an image-only semantic segmentation network and appending the class scores to each point. The appended (painted) point cloud can then be fed to any lidar-only method. Experiments show large improvements on three different state-of-the art methods, Point-RCNN, VoxelNet and PointPillars on the KITTI and nuScenes datasets. The painted version of PointRCNN represents a new state of the art on the KITTI leaderboard for the bird's-eye view detection task. In ablation, we study how the effects of Painting depends on the quality and format of the semantic segmentation output, and demonstrate how latency can be minimized through pipelining." @default.
- W2989996808 created "2019-12-05" @default.
- W2989996808 creator A5004716188 @default.
- W2989996808 creator A5011191730 @default.
- W2989996808 creator A5011966351 @default.
- W2989996808 creator A5047815467 @default.
- W2989996808 date "2019-11-22" @default.
- W2989996808 modified "2023-09-28" @default.
- W2989996808 title "PointPainting: Sequential Fusion for 3D Object Detection" @default.
- W2989996808 cites W1903029394 @default.
- W2989996808 cites W2150066425 @default.
- W2989996808 cites W2194775991 @default.
- W2989996808 cites W2340897893 @default.
- W2989996808 cites W2555618208 @default.
- W2989996808 cites W2781228439 @default.
- W2989996808 cites W2793066252 @default.
- W2989996808 cites W2795247881 @default.
- W2989996808 cites W2798965597 @default.
- W2989996808 cites W2894705404 @default.
- W2989996808 cites W2894961607 @default.
- W2989996808 cites W2895946091 @default.
- W2989996808 cites W2897529137 @default.
- W2989996808 cites W2904140919 @default.
- W2989996808 cites W2919534447 @default.
- W2989996808 cites W2949708697 @default.
- W2989996808 cites W2954174912 @default.
- W2989996808 cites W2963083779 @default.
- W2989996808 cites W2963120444 @default.
- W2989996808 cites W2963400571 @default.
- W2989996808 cites W2963576229 @default.
- W2989996808 cites W2963727135 @default.
- W2989996808 cites W2964062501 @default.
- W2989996808 cites W2964212410 @default.
- W2989996808 cites W2964254867 @default.
- W2989996808 cites W2964309882 @default.
- W2989996808 cites W2968296999 @default.
- W2989996808 cites W2969987486 @default.
- W2989996808 cites W2981857055 @default.
- W2989996808 cites W2996166203 @default.
- W2989996808 cites W2997790735 @default.
- W2989996808 cites W3021304778 @default.
- W2989996808 cites W3035574168 @default.
- W2989996808 hasPublicationYear "2019" @default.
- W2989996808 type Work @default.
- W2989996808 sameAs 2989996808 @default.
- W2989996808 citedByCount "7" @default.
- W2989996808 countsByYear W29899968082019 @default.
- W2989996808 countsByYear W29899968082020 @default.
- W2989996808 countsByYear W29899968082021 @default.
- W2989996808 crossrefType "posted-content" @default.
- W2989996808 hasAuthorship W2989996808A5004716188 @default.
- W2989996808 hasAuthorship W2989996808A5011191730 @default.
- W2989996808 hasAuthorship W2989996808A5011966351 @default.
- W2989996808 hasAuthorship W2989996808A5047815467 @default.
- W2989996808 hasConcept C131979681 @default.
- W2989996808 hasConcept C13280743 @default.
- W2989996808 hasConcept C138885662 @default.
- W2989996808 hasConcept C154945302 @default.
- W2989996808 hasConcept C158525013 @default.
- W2989996808 hasConcept C185798385 @default.
- W2989996808 hasConcept C205649164 @default.
- W2989996808 hasConcept C2524010 @default.
- W2989996808 hasConcept C2776151529 @default.
- W2989996808 hasConcept C28719098 @default.
- W2989996808 hasConcept C31972630 @default.
- W2989996808 hasConcept C33923547 @default.
- W2989996808 hasConcept C41008148 @default.
- W2989996808 hasConcept C41895202 @default.
- W2989996808 hasConcept C51399673 @default.
- W2989996808 hasConcept C62649853 @default.
- W2989996808 hasConcept C89600930 @default.
- W2989996808 hasConceptScore W2989996808C131979681 @default.
- W2989996808 hasConceptScore W2989996808C13280743 @default.
- W2989996808 hasConceptScore W2989996808C138885662 @default.
- W2989996808 hasConceptScore W2989996808C154945302 @default.
- W2989996808 hasConceptScore W2989996808C158525013 @default.
- W2989996808 hasConceptScore W2989996808C185798385 @default.
- W2989996808 hasConceptScore W2989996808C205649164 @default.
- W2989996808 hasConceptScore W2989996808C2524010 @default.
- W2989996808 hasConceptScore W2989996808C2776151529 @default.
- W2989996808 hasConceptScore W2989996808C28719098 @default.
- W2989996808 hasConceptScore W2989996808C31972630 @default.
- W2989996808 hasConceptScore W2989996808C33923547 @default.
- W2989996808 hasConceptScore W2989996808C41008148 @default.
- W2989996808 hasConceptScore W2989996808C41895202 @default.
- W2989996808 hasConceptScore W2989996808C51399673 @default.
- W2989996808 hasConceptScore W2989996808C62649853 @default.
- W2989996808 hasConceptScore W2989996808C89600930 @default.
- W2989996808 hasOpenAccess W2989996808 @default.
- W2989996808 hasRelatedWork W2115579991 @default.
- W2989996808 hasRelatedWork W2555618208 @default.
- W2989996808 hasRelatedWork W2560609797 @default.
- W2989996808 hasRelatedWork W2798965597 @default.
- W2989996808 hasRelatedWork W2894705404 @default.
- W2989996808 hasRelatedWork W2949708697 @default.
- W2989996808 hasRelatedWork W2951517617 @default.
- W2989996808 hasRelatedWork W2954174912 @default.
- W2989996808 hasRelatedWork W2962888833 @default.
- W2989996808 hasRelatedWork W2963121255 @default.
- W2989996808 hasRelatedWork W2963400571 @default.