Matches in SemOpenAlex for { <https://semopenalex.org/work/W3014703304> ?p ?o ?g. }
- W3014703304 abstract "In this work we study the mutual benefits of two common computer vision tasks, self-supervised depth estimation and semantic segmentation from images. For example, to help unsupervised monocular depth estimation, constraints from semantic segmentation has been explored implicitly such as sharing and transforming features. In contrast, we propose to explicitly measure the border consistency between segmentation and depth and minimize it in a greedy manner by iteratively supervising the network towards a locally optimal solution. Partially this is motivated by our observation that semantic segmentation even trained with limited ground truth (200 images of KITTI) can offer more accurate border than that of any (monocular or stereo) image-based depth estimation. Through extensive experiments, our proposed approach advances the state of the art on unsupervised monocular depth estimation in the KITTI." @default.
- W3014703304 created "2020-04-10" @default.
- W3014703304 creator A5077998492 @default.
- W3014703304 creator A5085264811 @default.
- W3014703304 creator A5090992450 @default.
- W3014703304 date "2020-03-31" @default.
- W3014703304 modified "2023-10-17" @default.
- W3014703304 title "The Edge of Depth: Explicit Constraints between Segmentation and Depth" @default.
- W3014703304 cites W1915250530 @default.
- W3014703304 cites W2046911213 @default.
- W3014703304 cites W2108598243 @default.
- W3014703304 cites W2117248802 @default.
- W3014703304 cites W2133665775 @default.
- W3014703304 cites W2150066425 @default.
- W3014703304 cites W2165114467 @default.
- W3014703304 cites W2176412452 @default.
- W3014703304 cites W2194775991 @default.
- W3014703304 cites W2300779272 @default.
- W3014703304 cites W2340897893 @default.
- W3014703304 cites W2593414960 @default.
- W3014703304 cites W2608018946 @default.
- W3014703304 cites W2609883120 @default.
- W3014703304 cites W2618011341 @default.
- W3014703304 cites W2767981409 @default.
- W3014703304 cites W2830339951 @default.
- W3014703304 cites W2886322387 @default.
- W3014703304 cites W2887848798 @default.
- W3014703304 cites W2894788161 @default.
- W3014703304 cites W2894983388 @default.
- W3014703304 cites W2896047481 @default.
- W3014703304 cites W2897203992 @default.
- W3014703304 cites W2899771611 @default.
- W3014703304 cites W2902918442 @default.
- W3014703304 cites W2934279571 @default.
- W3014703304 cites W2948647700 @default.
- W3014703304 cites W2949117887 @default.
- W3014703304 cites W2949634581 @default.
- W3014703304 cites W2951234442 @default.
- W3014703304 cites W2952825894 @default.
- W3014703304 cites W2959581809 @default.
- W3014703304 cites W2962816904 @default.
- W3014703304 cites W2962960377 @default.
- W3014703304 cites W2963061226 @default.
- W3014703304 cites W2963265330 @default.
- W3014703304 cites W2963412495 @default.
- W3014703304 cites W2963488291 @default.
- W3014703304 cites W2963583471 @default.
- W3014703304 cites W2963677766 @default.
- W3014703304 cites W2964020152 @default.
- W3014703304 cites W2967550825 @default.
- W3014703304 cites W2973110888 @default.
- W3014703304 cites W2981518351 @default.
- W3014703304 cites W2982012700 @default.
- W3014703304 cites W2985775862 @default.
- W3014703304 cites W2999947750 @default.
- W3014703304 doi "https://doi.org/10.48550/arxiv.2004.00171" @default.
- W3014703304 hasPublicationYear "2020" @default.
- W3014703304 type Work @default.
- W3014703304 sameAs 3014703304 @default.
- W3014703304 citedByCount "4" @default.
- W3014703304 countsByYear W30147033042020 @default.
- W3014703304 countsByYear W30147033042021 @default.
- W3014703304 crossrefType "posted-content" @default.
- W3014703304 hasAuthorship W3014703304A5077998492 @default.
- W3014703304 hasAuthorship W3014703304A5085264811 @default.
- W3014703304 hasAuthorship W3014703304A5090992450 @default.
- W3014703304 hasBestOaLocation W30147033041 @default.
- W3014703304 hasConcept C115961682 @default.
- W3014703304 hasConcept C124504099 @default.
- W3014703304 hasConcept C146849305 @default.
- W3014703304 hasConcept C153180895 @default.
- W3014703304 hasConcept C154945302 @default.
- W3014703304 hasConcept C162307627 @default.
- W3014703304 hasConcept C169760540 @default.
- W3014703304 hasConcept C26760741 @default.
- W3014703304 hasConcept C2776436953 @default.
- W3014703304 hasConcept C2776502983 @default.
- W3014703304 hasConcept C31972630 @default.
- W3014703304 hasConcept C41008148 @default.
- W3014703304 hasConcept C52672216 @default.
- W3014703304 hasConcept C65909025 @default.
- W3014703304 hasConcept C86803240 @default.
- W3014703304 hasConcept C89600930 @default.
- W3014703304 hasConceptScore W3014703304C115961682 @default.
- W3014703304 hasConceptScore W3014703304C124504099 @default.
- W3014703304 hasConceptScore W3014703304C146849305 @default.
- W3014703304 hasConceptScore W3014703304C153180895 @default.
- W3014703304 hasConceptScore W3014703304C154945302 @default.
- W3014703304 hasConceptScore W3014703304C162307627 @default.
- W3014703304 hasConceptScore W3014703304C169760540 @default.
- W3014703304 hasConceptScore W3014703304C26760741 @default.
- W3014703304 hasConceptScore W3014703304C2776436953 @default.
- W3014703304 hasConceptScore W3014703304C2776502983 @default.
- W3014703304 hasConceptScore W3014703304C31972630 @default.
- W3014703304 hasConceptScore W3014703304C41008148 @default.
- W3014703304 hasConceptScore W3014703304C52672216 @default.
- W3014703304 hasConceptScore W3014703304C65909025 @default.
- W3014703304 hasConceptScore W3014703304C86803240 @default.
- W3014703304 hasConceptScore W3014703304C89600930 @default.
- W3014703304 hasLocation W30147033041 @default.