Matches in SemOpenAlex for { <https://semopenalex.org/work/W2966400516> ?p ?o ?g. }
- W2966400516 abstract "Estimating depth from a single image represents an attractive alternative to more traditional approaches leveraging multiple cameras. In this field, deep learning yielded outstanding results at the cost of needing large amounts of data labeled with precise depth measurements for training. An issue softened by self-supervised approaches leveraging monocular sequences or stereo pairs in place of expensive ground truth depth annotations. This paper enables to further improve monocular depth estimation by integrating into existing self-supervised networks a geometrical prior. Specifically, we propose a sparsity-invariant autoencoder able to process the output of conventional visual odometry algorithms working in synergy with depth-from-mono networks. Experimental results on the KITTI dataset show that by exploiting the geometrical prior, our proposal: i) outperforms existing approaches in the literature and ii) couples well with both compact and complex depth-from-mono architectures, allowing for its deployment on high-end GPUs as well as on embedded devices (e.g., NVIDIA Jetson TX2)." @default.
- W2966400516 created "2019-08-13" @default.
- W2966400516 creator A5001469173 @default.
- W2966400516 creator A5036563362 @default.
- W2966400516 creator A5037548245 @default.
- W2966400516 creator A5067538897 @default.
- W2966400516 creator A5072569849 @default.
- W2966400516 creator A5074570544 @default.
- W2966400516 creator A5083926537 @default.
- W2966400516 date "2019-08-08" @default.
- W2966400516 modified "2023-09-27" @default.
- W2966400516 title "Enhancing self-supervised monocular depth estimation with traditional visual odometry" @default.
- W2966400516 cites W1803059841 @default.
- W2966400516 cites W1992178727 @default.
- W2966400516 cites W2033819227 @default.
- W2966400516 cites W2108134361 @default.
- W2966400516 cites W2117248802 @default.
- W2966400516 cites W2132947399 @default.
- W2966400516 cites W2133665775 @default.
- W2966400516 cites W2143291846 @default.
- W2966400516 cites W2150066425 @default.
- W2966400516 cites W2194775991 @default.
- W2966400516 cites W2218842719 @default.
- W2966400516 cites W2484274495 @default.
- W2966400516 cites W2520707372 @default.
- W2966400516 cites W2606794968 @default.
- W2966400516 cites W2609883120 @default.
- W2966400516 cites W2741799997 @default.
- W2966400516 cites W2750215633 @default.
- W2966400516 cites W2779522084 @default.
- W2966400516 cites W2798414551 @default.
- W2966400516 cites W2830339951 @default.
- W2966400516 cites W2886322387 @default.
- W2966400516 cites W2887848798 @default.
- W2966400516 cites W2889061519 @default.
- W2966400516 cites W2890949887 @default.
- W2966400516 cites W2892143204 @default.
- W2966400516 cites W2895192073 @default.
- W2966400516 cites W2897203992 @default.
- W2966400516 cites W2913483780 @default.
- W2966400516 cites W2934279571 @default.
- W2966400516 cites W2945594346 @default.
- W2966400516 cites W2949634581 @default.
- W2966400516 cites W2950971522 @default.
- W2966400516 cites W2951234442 @default.
- W2966400516 cites W2951333975 @default.
- W2966400516 cites W2953139137 @default.
- W2966400516 cites W2962816904 @default.
- W2966400516 cites W2963045776 @default.
- W2966400516 cites W2963417597 @default.
- W2966400516 cites W2963488291 @default.
- W2966400516 cites W2963583471 @default.
- W2966400516 cites W2963591054 @default.
- W2966400516 cites W2963654727 @default.
- W2966400516 cites W2963906250 @default.
- W2966400516 cites W2964014680 @default.
- W2966400516 cites W2964020152 @default.
- W2966400516 cites W2964052474 @default.
- W2966400516 cites W2964110533 @default.
- W2966400516 cites W2964121744 @default.
- W2966400516 cites W2968529893 @default.
- W2966400516 cites W3102327032 @default.
- W2966400516 cites W612478963 @default.
- W2966400516 hasPublicationYear "2019" @default.
- W2966400516 type Work @default.
- W2966400516 sameAs 2966400516 @default.
- W2966400516 citedByCount "0" @default.
- W2966400516 crossrefType "posted-content" @default.
- W2966400516 hasAuthorship W2966400516A5001469173 @default.
- W2966400516 hasAuthorship W2966400516A5036563362 @default.
- W2966400516 hasAuthorship W2966400516A5037548245 @default.
- W2966400516 hasAuthorship W2966400516A5067538897 @default.
- W2966400516 hasAuthorship W2966400516A5072569849 @default.
- W2966400516 hasAuthorship W2966400516A5074570544 @default.
- W2966400516 hasAuthorship W2966400516A5083926537 @default.
- W2966400516 hasConcept C101738243 @default.
- W2966400516 hasConcept C105339364 @default.
- W2966400516 hasConcept C108583219 @default.
- W2966400516 hasConcept C111919701 @default.
- W2966400516 hasConcept C115961682 @default.
- W2966400516 hasConcept C141268832 @default.
- W2966400516 hasConcept C146849305 @default.
- W2966400516 hasConcept C153180895 @default.
- W2966400516 hasConcept C154945302 @default.
- W2966400516 hasConcept C190470478 @default.
- W2966400516 hasConcept C19966478 @default.
- W2966400516 hasConcept C31972630 @default.
- W2966400516 hasConcept C33923547 @default.
- W2966400516 hasConcept C37914503 @default.
- W2966400516 hasConcept C41008148 @default.
- W2966400516 hasConcept C49441653 @default.
- W2966400516 hasConcept C5799516 @default.
- W2966400516 hasConcept C65909025 @default.
- W2966400516 hasConcept C90509273 @default.
- W2966400516 hasConcept C98045186 @default.
- W2966400516 hasConceptScore W2966400516C101738243 @default.
- W2966400516 hasConceptScore W2966400516C105339364 @default.
- W2966400516 hasConceptScore W2966400516C108583219 @default.
- W2966400516 hasConceptScore W2966400516C111919701 @default.
- W2966400516 hasConceptScore W2966400516C115961682 @default.