Matches in SemOpenAlex for { <https://semopenalex.org/work/W3112797573> ?p ?o ?g. }
- W3112797573 endingPage "128" @default.
- W3112797573 startingPage "118" @default.
- W3112797573 abstract "In this paper, we propose a self-supervised optical flow-based approach to learn the rotation of an arbitrarily moving spherical camera. Nowadays, deep learning has enabled efficient learning of camera rotation efficiently. However, most approaches are fully supervised and require large datasets with ground-truth labels of the rotation, and these labels are difficult to acquire. We attempt to solve this problem by using a derotation operation of the spherical optical flow on a unit sphere. This operation decouples the camera rotation from the mixture of translational and rotational components, removing the effect of 3D information for rotation estimation. Therefore, we integrate a derotation layer into a convolutional neural network for regressing the camera rotation. This layer can be adopted for only spherical cameras, which can capture all-round information, and thus enables the network to be learned the camera rotation without using labeled training datasets. We experimentally demonstrate that our approach achieves the comparable performance for the rotation estimation to that of a fully supervised approach and that it outperforms a previously proposed approach. Moreover, transfer learning is conducted in new environments to confirm the benefit of the self-supervised learning." @default.
- W3112797573 created "2020-12-21" @default.
- W3112797573 creator A5021260328 @default.
- W3112797573 creator A5043643094 @default.
- W3112797573 creator A5045114877 @default.
- W3112797573 creator A5064103302 @default.
- W3112797573 creator A5071567570 @default.
- W3112797573 date "2020-12-09" @default.
- W3112797573 modified "2023-10-01" @default.
- W3112797573 title "Self-supervised optical flow derotation network for rotation estimation of a spherical camera" @default.
- W3112797573 cites W1513100184 @default.
- W3112797573 cites W1930563420 @default.
- W3112797573 cites W1951289974 @default.
- W3112797573 cites W2096366269 @default.
- W3112797573 cites W2101938307 @default.
- W3112797573 cites W2113221323 @default.
- W3112797573 cites W2115579991 @default.
- W3112797573 cites W2200124539 @default.
- W3112797573 cites W2220063164 @default.
- W3112797573 cites W2509776007 @default.
- W3112797573 cites W2564632156 @default.
- W3112797573 cites W2580748890 @default.
- W3112797573 cites W2598706937 @default.
- W3112797573 cites W2609883120 @default.
- W3112797573 cites W2615725379 @default.
- W3112797573 cites W2738767782 @default.
- W3112797573 cites W2786585376 @default.
- W3112797573 cites W2797395780 @default.
- W3112797573 cites W2801955291 @default.
- W3112797573 cites W2887843334 @default.
- W3112797573 cites W2890829694 @default.
- W3112797573 cites W2891342280 @default.
- W3112797573 cites W2900510798 @default.
- W3112797573 cites W2903541310 @default.
- W3112797573 cites W2909593838 @default.
- W3112797573 cites W2937084899 @default.
- W3112797573 cites W2944474001 @default.
- W3112797573 cites W2950989657 @default.
- W3112797573 cites W2952348863 @default.
- W3112797573 cites W2954269264 @default.
- W3112797573 cites W2963189264 @default.
- W3112797573 cites W2963403249 @default.
- W3112797573 cites W2963583471 @default.
- W3112797573 cites W2964206229 @default.
- W3112797573 cites W2964851543 @default.
- W3112797573 cites W2985775862 @default.
- W3112797573 cites W3007404071 @default.
- W3112797573 cites W3100388886 @default.
- W3112797573 cites W3104255671 @default.
- W3112797573 doi "https://doi.org/10.1080/01691864.2020.1857305" @default.
- W3112797573 hasPublicationYear "2020" @default.
- W3112797573 type Work @default.
- W3112797573 sameAs 3112797573 @default.
- W3112797573 citedByCount "3" @default.
- W3112797573 countsByYear W31127975732022 @default.
- W3112797573 countsByYear W31127975732023 @default.
- W3112797573 crossrefType "journal-article" @default.
- W3112797573 hasAuthorship W3112797573A5021260328 @default.
- W3112797573 hasAuthorship W3112797573A5043643094 @default.
- W3112797573 hasAuthorship W3112797573A5045114877 @default.
- W3112797573 hasAuthorship W3112797573A5064103302 @default.
- W3112797573 hasAuthorship W3112797573A5071567570 @default.
- W3112797573 hasConcept C115961682 @default.
- W3112797573 hasConcept C136389625 @default.
- W3112797573 hasConcept C146849305 @default.
- W3112797573 hasConcept C150899416 @default.
- W3112797573 hasConcept C153180895 @default.
- W3112797573 hasConcept C154945302 @default.
- W3112797573 hasConcept C155542232 @default.
- W3112797573 hasConcept C2524010 @default.
- W3112797573 hasConcept C31972630 @default.
- W3112797573 hasConcept C33923547 @default.
- W3112797573 hasConcept C38349280 @default.
- W3112797573 hasConcept C41008148 @default.
- W3112797573 hasConcept C50644808 @default.
- W3112797573 hasConcept C74050887 @default.
- W3112797573 hasConcept C81363708 @default.
- W3112797573 hasConceptScore W3112797573C115961682 @default.
- W3112797573 hasConceptScore W3112797573C136389625 @default.
- W3112797573 hasConceptScore W3112797573C146849305 @default.
- W3112797573 hasConceptScore W3112797573C150899416 @default.
- W3112797573 hasConceptScore W3112797573C153180895 @default.
- W3112797573 hasConceptScore W3112797573C154945302 @default.
- W3112797573 hasConceptScore W3112797573C155542232 @default.
- W3112797573 hasConceptScore W3112797573C2524010 @default.
- W3112797573 hasConceptScore W3112797573C31972630 @default.
- W3112797573 hasConceptScore W3112797573C33923547 @default.
- W3112797573 hasConceptScore W3112797573C38349280 @default.
- W3112797573 hasConceptScore W3112797573C41008148 @default.
- W3112797573 hasConceptScore W3112797573C50644808 @default.
- W3112797573 hasConceptScore W3112797573C74050887 @default.
- W3112797573 hasConceptScore W3112797573C81363708 @default.
- W3112797573 hasFunder F4320334764 @default.
- W3112797573 hasIssue "2" @default.
- W3112797573 hasLocation W31127975731 @default.
- W3112797573 hasOpenAccess W3112797573 @default.
- W3112797573 hasPrimaryLocation W31127975731 @default.
- W3112797573 hasRelatedWork W2171116555 @default.