Matches in SemOpenAlex for { <https://semopenalex.org/work/W4200255358> ?p ?o ?g. }
Showing items 1 to 62 of
62
with 100 items per page.
- W4200255358 endingPage "646" @default.
- W4200255358 startingPage "634" @default.
- W4200255358 abstract "Learning monocular depth in a self-supervised manner is desirable for numerous applications ranging from autonomous driving, robotics to augmented reality. However, the current challenges lie in the problems of scale ambiguity, dynamic scene and hardware limitations. To this end, a self-supervised approach is proposed in this work for monocular depth learning and estimation. Specifically, we first introduce a self-supervised depth learning framework that learns a part of the camera intrinsics and the stereo extrinsics, which ensures the absoluteness of the predicted depth while achieving enhanced performance (i.e., lower error between the predicted depth and the ground-truth) on depth estimation. Besides, we further improve the accuracy and the efficiency (i.e., shorter inference time and lower weight/activation footprints) via a specially-designed network that exploits multi-scale context across multi-level feature maps. In addition, we propose a quantization scheme for our depth estimation networks. The scheme allows the network inference to be carried out using INT4-INT8 arithmetic while keeping a high performance on depth estimation. Extensive experiments on KITTI and Make3D datasets demonstrate that our approach substantially boosts the performance compared to the existing state-of-the-art methods on monocular depth estimation." @default.
- W4200255358 created "2021-12-31" @default.
- W4200255358 creator A5010263668 @default.
- W4200255358 creator A5028259707 @default.
- W4200255358 creator A5072930058 @default.
- W4200255358 date "2022-06-01" @default.
- W4200255358 modified "2023-10-05" @default.
- W4200255358 title "Self-supervised learning of monocular depth using quantized networks" @default.
- W4200255358 cites W1803059841 @default.
- W4200255358 cites W2041318191 @default.
- W4200255358 cites W2117539524 @default.
- W4200255358 cites W2133665775 @default.
- W4200255358 cites W2300779272 @default.
- W4200255358 cites W2593414960 @default.
- W4200255358 cites W2766555673 @default.
- W4200255358 cites W2788857104 @default.
- W4200255358 cites W2963412495 @default.
- W4200255358 cites W2992582397 @default.
- W4200255358 doi "https://doi.org/10.1016/j.neucom.2021.11.071" @default.
- W4200255358 hasPublicationYear "2022" @default.
- W4200255358 type Work @default.
- W4200255358 citedByCount "2" @default.
- W4200255358 countsByYear W42002553582023 @default.
- W4200255358 crossrefType "journal-article" @default.
- W4200255358 hasAuthorship W4200255358A5010263668 @default.
- W4200255358 hasAuthorship W4200255358A5028259707 @default.
- W4200255358 hasAuthorship W4200255358A5072930058 @default.
- W4200255358 hasConcept C119857082 @default.
- W4200255358 hasConcept C136389625 @default.
- W4200255358 hasConcept C153180895 @default.
- W4200255358 hasConcept C154945302 @default.
- W4200255358 hasConcept C41008148 @default.
- W4200255358 hasConcept C50644808 @default.
- W4200255358 hasConcept C58973888 @default.
- W4200255358 hasConcept C65909025 @default.
- W4200255358 hasConceptScore W4200255358C119857082 @default.
- W4200255358 hasConceptScore W4200255358C136389625 @default.
- W4200255358 hasConceptScore W4200255358C153180895 @default.
- W4200255358 hasConceptScore W4200255358C154945302 @default.
- W4200255358 hasConceptScore W4200255358C41008148 @default.
- W4200255358 hasConceptScore W4200255358C50644808 @default.
- W4200255358 hasConceptScore W4200255358C58973888 @default.
- W4200255358 hasConceptScore W4200255358C65909025 @default.
- W4200255358 hasLocation W42002553581 @default.
- W4200255358 hasOpenAccess W4200255358 @default.
- W4200255358 hasPrimaryLocation W42002553581 @default.
- W4200255358 hasRelatedWork W122912556 @default.
- W4200255358 hasRelatedWork W1756896031 @default.
- W4200255358 hasRelatedWork W3025582806 @default.
- W4200255358 hasRelatedWork W3094076422 @default.
- W4200255358 hasRelatedWork W3162567751 @default.
- W4200255358 hasRelatedWork W4285260836 @default.
- W4200255358 hasRelatedWork W4306321456 @default.
- W4200255358 hasRelatedWork W4312414840 @default.
- W4200255358 hasRelatedWork W4319309271 @default.
- W4200255358 hasRelatedWork W4386025632 @default.
- W4200255358 hasVolume "488" @default.
- W4200255358 isParatext "false" @default.
- W4200255358 isRetracted "false" @default.
- W4200255358 workType "article" @default.