Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308486818> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W4308486818 endingPage "221" @default.
- W4308486818 startingPage "209" @default.
- W4308486818 abstract "Accurate camera localization in existing LiDAR maps is promising since it potentially allows exploiting strengths of both LiDAR-based and camera-based methods. However, effective methods that robustly address appearance and modality differences for 2D–3D localization are still missing. To overcome these problems, we propose the I2D-Loc, a scene-agnostic and end-to-end trainable neural network that estimates the 6-DoF pose from an RGB image to an existing LiDAR map with local optimization on an initial pose. Specifically, we first project the LiDAR map to the image plane according to a rough initial pose and utilize a depth completion algorithm to generate a dense depth image. We further design a confidence map to weight the features extracted from the dense depth to get a more reliable depth representation. Then, we propose to utilize a neural network to estimate the correspondence flow between depth and RGB images. Finally, we utilize the BPnP algorithm to estimate the 6-DoF pose, calculating the gradients of pose error and optimizing the front-end network parameters. Moreover, by decoupling the intrinsic camera parameters out of the end-to-end training process, I2D-Loc can be generalized to the images with different intrinsic parameters. Experiments on KITTI, Argoverse, and Lyft5 datasets demonstrate that the I2D-Loc can achieve centimeter localization performance. The source code, dataset, trained models, and demo videos are released at https://levenberg.github.io/I2D-Loc/ ." @default.
- W4308486818 created "2022-11-12" @default.
- W4308486818 creator A5032584934 @default.
- W4308486818 creator A5067222034 @default.
- W4308486818 creator A5069540177 @default.
- W4308486818 creator A5073032922 @default.
- W4308486818 creator A5076179689 @default.
- W4308486818 creator A5091253394 @default.
- W4308486818 date "2022-12-01" @default.
- W4308486818 modified "2023-09-24" @default.
- W4308486818 title "I2D-Loc: Camera localization via image to LiDAR depth flow" @default.
- W4308486818 cites W1991544872 @default.
- W4308486818 cites W2061246543 @default.
- W4308486818 cites W2115579991 @default.
- W4308486818 cites W2191707460 @default.
- W4308486818 cites W2522940611 @default.
- W4308486818 cites W2745859992 @default.
- W4308486818 cites W2809106465 @default.
- W4308486818 cites W2922374969 @default.
- W4308486818 cites W2954297243 @default.
- W4308486818 cites W3032893832 @default.
- W4308486818 cites W3040403216 @default.
- W4308486818 cites W3102327032 @default.
- W4308486818 cites W3141835154 @default.
- W4308486818 cites W3177438851 @default.
- W4308486818 cites W4206728461 @default.
- W4308486818 doi "https://doi.org/10.1016/j.isprsjprs.2022.10.009" @default.
- W4308486818 hasPublicationYear "2022" @default.
- W4308486818 type Work @default.
- W4308486818 citedByCount "0" @default.
- W4308486818 crossrefType "journal-article" @default.
- W4308486818 hasAuthorship W4308486818A5032584934 @default.
- W4308486818 hasAuthorship W4308486818A5067222034 @default.
- W4308486818 hasAuthorship W4308486818A5069540177 @default.
- W4308486818 hasAuthorship W4308486818A5073032922 @default.
- W4308486818 hasAuthorship W4308486818A5076179689 @default.
- W4308486818 hasAuthorship W4308486818A5091253394 @default.
- W4308486818 hasConcept C115961682 @default.
- W4308486818 hasConcept C121684516 @default.
- W4308486818 hasConcept C127313418 @default.
- W4308486818 hasConcept C154945302 @default.
- W4308486818 hasConcept C155542232 @default.
- W4308486818 hasConcept C31972630 @default.
- W4308486818 hasConcept C41008148 @default.
- W4308486818 hasConcept C51399673 @default.
- W4308486818 hasConcept C62649853 @default.
- W4308486818 hasConceptScore W4308486818C115961682 @default.
- W4308486818 hasConceptScore W4308486818C121684516 @default.
- W4308486818 hasConceptScore W4308486818C127313418 @default.
- W4308486818 hasConceptScore W4308486818C154945302 @default.
- W4308486818 hasConceptScore W4308486818C155542232 @default.
- W4308486818 hasConceptScore W4308486818C31972630 @default.
- W4308486818 hasConceptScore W4308486818C41008148 @default.
- W4308486818 hasConceptScore W4308486818C51399673 @default.
- W4308486818 hasConceptScore W4308486818C62649853 @default.
- W4308486818 hasFunder F4320321001 @default.
- W4308486818 hasFunder F4320322186 @default.
- W4308486818 hasFunder F4320324116 @default.
- W4308486818 hasFunder F4320335787 @default.
- W4308486818 hasLocation W43084868181 @default.
- W4308486818 hasOpenAccess W4308486818 @default.
- W4308486818 hasPrimaryLocation W43084868181 @default.
- W4308486818 hasRelatedWork W1965104004 @default.
- W4308486818 hasRelatedWork W2042745137 @default.
- W4308486818 hasRelatedWork W2123374136 @default.
- W4308486818 hasRelatedWork W2130194352 @default.
- W4308486818 hasRelatedWork W2171116555 @default.
- W4308486818 hasRelatedWork W2244560705 @default.
- W4308486818 hasRelatedWork W2900363363 @default.
- W4308486818 hasRelatedWork W3098068165 @default.
- W4308486818 hasRelatedWork W4281553171 @default.
- W4308486818 hasRelatedWork W1501270482 @default.
- W4308486818 hasVolume "194" @default.
- W4308486818 isParatext "false" @default.
- W4308486818 isRetracted "false" @default.
- W4308486818 workType "article" @default.