Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285102194> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W4285102194 abstract "Accurate camera pose estimation is a fundamental requirement for numerous applications, such as autonomous driving, mobile robotics, and augmented reality. In this work, we address the problem of estimating the global 6 DoF camera pose from a single RGB image in a given environment. Previous works consider every part of the image valuable for localization. However, many image regions such as the sky, occlusions, and repetitive non-distinguishable patterns cannot be utilized for localization. In addition to adding unnecessary computation efforts, extracting and matching features from such regions pro-duce many wrong matches which in turn degrades the localization accuracy and efficiency. Our work addresses this particular issue and shows by exploiting an interesting concept of sparse 3D models that we can exploit discriminatory environment parts and avoid useless image regions for the sake of a single image localization. Interestingly, through avoiding selecting keypoints from non-reliable image regions such as trees, bushes, cars, pedestrians, and occlusions, our work acts naturally as an outlier filter. This makes our system highly efficient in that minimal set of correspondences is needed and highly accurate as the number of outliers is low. Our work exceeds state-of-the-art methods on outdoor Cambridge Landmarks dataset. With only relying on single image at inference, it outweighs in terms of accuracy methods that exploit pose priors and/or reference 3D models while being much faster. By choosing as little as 100 correspondences, it surpasses similar methods that localize from thousands of correspondences, while being more efficient. In particular, it achieves, compared to these methods, an improvement of localization by 33% on OldHospital scene. Furthermore, It outstands direct pose regressors even those that learn from sequence of images. Our work will be publicly available." @default.
- W4285102194 created "2022-07-14" @default.
- W4285102194 creator A5001923349 @default.
- W4285102194 date "2022-05-23" @default.
- W4285102194 modified "2023-09-23" @default.
- W4285102194 title "PixSelect: Less but Reliable Pixels for Accurate and Efficient Localization" @default.
- W4285102194 cites W1989476314 @default.
- W4285102194 cites W1991544872 @default.
- W4285102194 cites W2085261163 @default.
- W4285102194 cites W2097649661 @default.
- W4285102194 cites W2129000642 @default.
- W4285102194 cites W2200124539 @default.
- W4285102194 cites W2471962767 @default.
- W4285102194 cites W2522940611 @default.
- W4285102194 cites W2556455135 @default.
- W4285102194 cites W2584731199 @default.
- W4285102194 cites W2605111497 @default.
- W4285102194 cites W2749379418 @default.
- W4285102194 cites W2795645133 @default.
- W4285102194 cites W2922243907 @default.
- W4285102194 cites W2962799344 @default.
- W4285102194 cites W2963856988 @default.
- W4285102194 cites W2987672160 @default.
- W4285102194 cites W2995503268 @default.
- W4285102194 cites W2997032998 @default.
- W4285102194 cites W3100388886 @default.
- W4285102194 cites W3176602998 @default.
- W4285102194 doi "https://doi.org/10.1109/icra46639.2022.9812345" @default.
- W4285102194 hasPublicationYear "2022" @default.
- W4285102194 type Work @default.
- W4285102194 citedByCount "0" @default.
- W4285102194 crossrefType "proceedings-article" @default.
- W4285102194 hasAuthorship W4285102194A5001923349 @default.
- W4285102194 hasBestOaLocation W42851021942 @default.
- W4285102194 hasConcept C105795698 @default.
- W4285102194 hasConcept C115961682 @default.
- W4285102194 hasConcept C153180895 @default.
- W4285102194 hasConcept C154945302 @default.
- W4285102194 hasConcept C160633673 @default.
- W4285102194 hasConcept C165064840 @default.
- W4285102194 hasConcept C165696696 @default.
- W4285102194 hasConcept C177264268 @default.
- W4285102194 hasConcept C199360897 @default.
- W4285102194 hasConcept C31972630 @default.
- W4285102194 hasConcept C33923547 @default.
- W4285102194 hasConcept C38652104 @default.
- W4285102194 hasConcept C41008148 @default.
- W4285102194 hasConcept C52102323 @default.
- W4285102194 hasConcept C79337645 @default.
- W4285102194 hasConcept C82990744 @default.
- W4285102194 hasConceptScore W4285102194C105795698 @default.
- W4285102194 hasConceptScore W4285102194C115961682 @default.
- W4285102194 hasConceptScore W4285102194C153180895 @default.
- W4285102194 hasConceptScore W4285102194C154945302 @default.
- W4285102194 hasConceptScore W4285102194C160633673 @default.
- W4285102194 hasConceptScore W4285102194C165064840 @default.
- W4285102194 hasConceptScore W4285102194C165696696 @default.
- W4285102194 hasConceptScore W4285102194C177264268 @default.
- W4285102194 hasConceptScore W4285102194C199360897 @default.
- W4285102194 hasConceptScore W4285102194C31972630 @default.
- W4285102194 hasConceptScore W4285102194C33923547 @default.
- W4285102194 hasConceptScore W4285102194C38652104 @default.
- W4285102194 hasConceptScore W4285102194C41008148 @default.
- W4285102194 hasConceptScore W4285102194C52102323 @default.
- W4285102194 hasConceptScore W4285102194C79337645 @default.
- W4285102194 hasConceptScore W4285102194C82990744 @default.
- W4285102194 hasLocation W42851021941 @default.
- W4285102194 hasLocation W42851021942 @default.
- W4285102194 hasOpenAccess W4285102194 @default.
- W4285102194 hasPrimaryLocation W42851021941 @default.
- W4285102194 hasRelatedWork W2562706118 @default.
- W4285102194 hasRelatedWork W2794187083 @default.
- W4285102194 hasRelatedWork W2822883015 @default.
- W4285102194 hasRelatedWork W2891001608 @default.
- W4285102194 hasRelatedWork W2997897143 @default.
- W4285102194 hasRelatedWork W3102636071 @default.
- W4285102194 hasRelatedWork W3115178140 @default.
- W4285102194 hasRelatedWork W4213228110 @default.
- W4285102194 hasRelatedWork W4313046826 @default.
- W4285102194 hasRelatedWork W4320809347 @default.
- W4285102194 isParatext "false" @default.
- W4285102194 isRetracted "false" @default.
- W4285102194 workType "article" @default.