FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3003669105> ?p ?o ?g. }

• W3003669105 endingPage "4142" @default.
• W3003669105 startingPage "4130" @default.
• W3003669105 abstract "In recent years, supervised deep learning methods have shown a great promise in dense depth estimation. However, massive high-quality training data are expensive and impractical to acquire. Alternatively, self-supervised learning-based depth estimators can learn the latent transformation from monocular or binocular video sequences by minimizing the photometric warp error between consecutive frames, but they suffer from the scale ambiguity problem or have difficulty in estimating precise pose changes between frames. In this paper, we propose a joint self-supervised deep learning pipeline for depth and ego-motion estimation by employing the advantages of adversarial learning and joint optimization with spatial-temporal geometrical constraints. The stereo reconstruction error provides the spatial geometric constraint to estimate the absolute scale depth. Meanwhile, the depth map with an absolute scale and a pre-trained pose network serves as a good starting point for direct visual odometry (DVO). DVO optimization based on spatial geometric constraints can result in a fine-grained ego-motion estimation with the additional backpropagation signals provided to the depth estimation network. Finally, the spatial and temporal domain-based reconstructed views are concatenated, and the iterative coupling optimization process is implemented in combination with the adversarial learning for accurate depth and precise ego-motion estimation. The experimental results show superior performance compared with state-of-the-art methods for monocular depth and ego-motion estimation on the KITTI dataset and a great generalization ability of the proposed approach." @default.
• W3003669105 created "2020-02-07" @default.
• W3003669105 creator A5034402485 @default.
• W3003669105 creator A5039832462 @default.
• W3003669105 creator A5041016651 @default.
• W3003669105 creator A5042401810 @default.
• W3003669105 creator A5044591447 @default.
• W3003669105 creator A5055905608 @default.
• W3003669105 creator A5071398995 @default.
• W3003669105 date "2020-01-01" @default.
• W3003669105 modified "2023-10-18" @default.
• W3003669105 title "Adversarial Learning for Joint Optimization of Depth and Ego-Motion" @default.
• W3003669105 cites W1803059841 @default.
• W3003669105 cites W1905829557 @default.
• W3003669105 cites W1915250530 @default.
• W3003669105 cites W1948751323 @default.
• W3003669105 cites W2035379092 @default.
• W3003669105 cites W2091226544 @default.
• W3003669105 cites W2132947399 @default.
• W3003669105 cites W2133665775 @default.
• W3003669105 cites W2150066425 @default.
• W3003669105 cites W2168676389 @default.
• W3003669105 cites W2200124539 @default.
• W3003669105 cites W2288122362 @default.
• W3003669105 cites W2300779272 @default.
• W3003669105 cites W2336968928 @default.
• W3003669105 cites W2339754110 @default.
• W3003669105 cites W2340897893 @default.
• W3003669105 cites W2520707372 @default.
• W3003669105 cites W2593414960 @default.
• W3003669105 cites W2598706937 @default.
• W3003669105 cites W2605938684 @default.
• W3003669105 cites W2609883120 @default.
• W3003669105 cites W2798414551 @default.
• W3003669105 cites W2803168974 @default.
• W3003669105 cites W2808629189 @default.
• W3003669105 cites W2830339951 @default.
• W3003669105 cites W2886322387 @default.
• W3003669105 cites W2889002172 @default.
• W3003669105 cites W2889061519 @default.
• W3003669105 cites W2890949887 @default.
• W3003669105 cites W2934279571 @default.
• W3003669105 cites W2962807621 @default.
• W3003669105 cites W2962816904 @default.
• W3003669105 cites W2963470893 @default.
• W3003669105 cites W2963488291 @default.
• W3003669105 cites W2963583471 @default.
• W3003669105 cites W2963591054 @default.
• W3003669105 cites W2963652981 @default.
• W3003669105 cites W2963654727 @default.
• W3003669105 cites W2963735494 @default.
• W3003669105 cites W2963906250 @default.
• W3003669105 cites W2964014680 @default.
• W3003669105 cites W2964020152 @default.
• W3003669105 cites W2964314455 @default.
• W3003669105 cites W2964814869 @default.
• W3003669105 cites W3103648783 @default.
• W3003669105 doi "https://doi.org/10.1109/tip.2020.2968751" @default.
• W3003669105 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/32011252" @default.
• W3003669105 hasPublicationYear "2020" @default.
• W3003669105 type Work @default.
• W3003669105 sameAs 3003669105 @default.
• W3003669105 citedByCount "14" @default.
• W3003669105 countsByYear W30036691052020 @default.
• W3003669105 countsByYear W30036691052021 @default.
• W3003669105 countsByYear W30036691052022 @default.
• W3003669105 countsByYear W30036691052023 @default.
• W3003669105 crossrefType "journal-article" @default.
• W3003669105 hasAuthorship W3003669105A5034402485 @default.
• W3003669105 hasAuthorship W3003669105A5039832462 @default.
• W3003669105 hasAuthorship W3003669105A5041016651 @default.
• W3003669105 hasAuthorship W3003669105A5042401810 @default.
• W3003669105 hasAuthorship W3003669105A5044591447 @default.
• W3003669105 hasAuthorship W3003669105A5055905608 @default.
• W3003669105 hasAuthorship W3003669105A5071398995 @default.
• W3003669105 hasConcept C10161872 @default.
• W3003669105 hasConcept C105795698 @default.
• W3003669105 hasConcept C108583219 @default.
• W3003669105 hasConcept C146159030 @default.
• W3003669105 hasConcept C153180895 @default.
• W3003669105 hasConcept C154945302 @default.
• W3003669105 hasConcept C155032097 @default.
• W3003669105 hasConcept C185429906 @default.
• W3003669105 hasConcept C31972630 @default.
• W3003669105 hasConcept C33923547 @default.
• W3003669105 hasConcept C41008148 @default.
• W3003669105 hasConcept C50644808 @default.
• W3003669105 hasConcept C65909025 @default.
• W3003669105 hasConceptScore W3003669105C10161872 @default.
• W3003669105 hasConceptScore W3003669105C105795698 @default.
• W3003669105 hasConceptScore W3003669105C108583219 @default.
• W3003669105 hasConceptScore W3003669105C146159030 @default.
• W3003669105 hasConceptScore W3003669105C153180895 @default.
• W3003669105 hasConceptScore W3003669105C154945302 @default.
• W3003669105 hasConceptScore W3003669105C155032097 @default.
• W3003669105 hasConceptScore W3003669105C185429906 @default.
• W3003669105 hasConceptScore W3003669105C31972630 @default.
• W3003669105 hasConceptScore W3003669105C33923547 @default.

• next