Matches in SemOpenAlex for { <https://semopenalex.org/work/W4214648088> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W4214648088 endingPage "103471" @default.
- W4214648088 startingPage "103471" @default.
- W4214648088 abstract "Learning-based camera ego-motion estimation has attracted increasing attention and has made impressive improvements. However, the accuracy of unsupervised paradigm is still limited, especially in complex dynamic environment. In this paper, we propose a rigid-aware self-supervised generative adversarial network (GAN) for camera ego-motion estimation, which can effectively learn the rigidity of the scene and improve the accuracy of ego-motion estimation by combining the pixel- and the structure-level perception. Specifically, a rigid-aware generator is first designed for joint unsupervised learning of optical flow, stereo depth and camera pose from two consecutive frames. Then, an iterative pose refinement strategy with rigidity learning is presented to reduce the impact of moving objects in scenes. To overcome the limitation of the purely pixel-wised photometric methods, a rigidity mask embedded discriminator is attached to perceive structural distortion artifacts in synthesized fake images, which encourages the generator to learn additional structure-level information to improve the accuracy of pose estimation. Experiments on the benchmark datasets show that our model achieves the state-of-the-art performance in terms of both RPE and ATE compared to recent GAN-based methods." @default.
- W4214648088 created "2022-03-02" @default.
- W4214648088 creator A5036542312 @default.
- W4214648088 creator A5066429300 @default.
- W4214648088 creator A5067452827 @default.
- W4214648088 creator A5069657989 @default.
- W4214648088 date "2022-06-01" @default.
- W4214648088 modified "2023-09-29" @default.
- W4214648088 title "Rigid-aware self-supervised GAN for camera ego-motion estimation" @default.
- W4214648088 cites W2015996585 @default.
- W4214648088 cites W2133665775 @default.
- W4214648088 cites W2220063164 @default.
- W4214648088 cites W2954269264 @default.
- W4214648088 cites W2963265330 @default.
- W4214648088 cites W3044667778 @default.
- W4214648088 cites W3100847195 @default.
- W4214648088 cites W3102327032 @default.
- W4214648088 cites W3103648783 @default.
- W4214648088 cites W3153150633 @default.
- W4214648088 cites W3197931399 @default.
- W4214648088 doi "https://doi.org/10.1016/j.dsp.2022.103471" @default.
- W4214648088 hasPublicationYear "2022" @default.
- W4214648088 type Work @default.
- W4214648088 citedByCount "2" @default.
- W4214648088 countsByYear W42146480882023 @default.
- W4214648088 crossrefType "journal-article" @default.
- W4214648088 hasAuthorship W4214648088A5036542312 @default.
- W4214648088 hasAuthorship W4214648088A5066429300 @default.
- W4214648088 hasAuthorship W4214648088A5067452827 @default.
- W4214648088 hasAuthorship W4214648088A5069657989 @default.
- W4214648088 hasConcept C10161872 @default.
- W4214648088 hasConcept C121332964 @default.
- W4214648088 hasConcept C127413603 @default.
- W4214648088 hasConcept C13280743 @default.
- W4214648088 hasConcept C154945302 @default.
- W4214648088 hasConcept C160343418 @default.
- W4214648088 hasConcept C160633673 @default.
- W4214648088 hasConcept C163258240 @default.
- W4214648088 hasConcept C185798385 @default.
- W4214648088 hasConcept C205649164 @default.
- W4214648088 hasConcept C2779803651 @default.
- W4214648088 hasConcept C2780992000 @default.
- W4214648088 hasConcept C31972630 @default.
- W4214648088 hasConcept C41008148 @default.
- W4214648088 hasConcept C62520636 @default.
- W4214648088 hasConcept C66938386 @default.
- W4214648088 hasConcept C76155785 @default.
- W4214648088 hasConcept C94915269 @default.
- W4214648088 hasConceptScore W4214648088C10161872 @default.
- W4214648088 hasConceptScore W4214648088C121332964 @default.
- W4214648088 hasConceptScore W4214648088C127413603 @default.
- W4214648088 hasConceptScore W4214648088C13280743 @default.
- W4214648088 hasConceptScore W4214648088C154945302 @default.
- W4214648088 hasConceptScore W4214648088C160343418 @default.
- W4214648088 hasConceptScore W4214648088C160633673 @default.
- W4214648088 hasConceptScore W4214648088C163258240 @default.
- W4214648088 hasConceptScore W4214648088C185798385 @default.
- W4214648088 hasConceptScore W4214648088C205649164 @default.
- W4214648088 hasConceptScore W4214648088C2779803651 @default.
- W4214648088 hasConceptScore W4214648088C2780992000 @default.
- W4214648088 hasConceptScore W4214648088C31972630 @default.
- W4214648088 hasConceptScore W4214648088C41008148 @default.
- W4214648088 hasConceptScore W4214648088C62520636 @default.
- W4214648088 hasConceptScore W4214648088C66938386 @default.
- W4214648088 hasConceptScore W4214648088C76155785 @default.
- W4214648088 hasConceptScore W4214648088C94915269 @default.
- W4214648088 hasLocation W42146480881 @default.
- W4214648088 hasOpenAccess W4214648088 @default.
- W4214648088 hasPrimaryLocation W42146480881 @default.
- W4214648088 hasRelatedWork W121273120 @default.
- W4214648088 hasRelatedWork W2090093270 @default.
- W4214648088 hasRelatedWork W2117070652 @default.
- W4214648088 hasRelatedWork W2145347751 @default.
- W4214648088 hasRelatedWork W2152301642 @default.
- W4214648088 hasRelatedWork W2337415362 @default.
- W4214648088 hasRelatedWork W2619371851 @default.
- W4214648088 hasRelatedWork W2963170156 @default.
- W4214648088 hasRelatedWork W3180352537 @default.
- W4214648088 hasRelatedWork W4312857205 @default.
- W4214648088 hasVolume "126" @default.
- W4214648088 isParatext "false" @default.
- W4214648088 isRetracted "false" @default.
- W4214648088 workType "article" @default.