FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3107156787> ?p ?o ?g. }

• W3107156787 endingPage "600" @default.
• W3107156787 startingPage "582" @default.
• W3107156787 abstract "Self-supervised monocular depth estimation presents a powerful method to obtain 3D scene information from single camera images, which is trainable on arbitrary image sequences without requiring depth labels, e.g., from a LiDAR sensor. In this work we present a new self-supervised semantically-guided depth estimation (SGDepth) method to deal with moving dynamic-class (DC) objects, such as moving cars and pedestrians, which violate the static-world assumptions typically made during training of such models. Specifically, we propose (i) mutually beneficial cross-domain training of (supervised) semantic segmentation and self-supervised depth estimation with task-specific network heads, (ii) a semantic masking scheme providing guidance to prevent moving DC objects from contaminating the photometric loss, and (iii) a detection method for frames with non-moving DC objects, from which the depth of DC objects can be learned. We demonstrate the performance of our method on several benchmarks, in particular on the Eigen split, where we exceed all baselines without test-time refinement." @default.
• W3107156787 created "2020-12-07" @default.
• W3107156787 creator A5002593702 @default.
• W3107156787 creator A5047354615 @default.
• W3107156787 creator A5083561103 @default.
• W3107156787 creator A5087307877 @default.
• W3107156787 date "2020-01-01" @default.
• W3107156787 modified "2023-10-14" @default.
• W3107156787 title "Self-supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic Guidance" @default.
• W3107156787 cites W1803059841 @default.
• W3107156787 cites W1905829557 @default.
• W3107156787 cites W1921093919 @default.
• W3107156787 cites W2037227137 @default.
• W3107156787 cites W2115579991 @default.
• W3107156787 cites W2117248802 @default.
• W3107156787 cites W2117539524 @default.
• W3107156787 cites W2133665775 @default.
• W3107156787 cites W2194775991 @default.
• W3107156787 cites W2300779272 @default.
• W3107156787 cites W2340897893 @default.
• W3107156787 cites W2427448504 @default.
• W3107156787 cites W2520707372 @default.
• W3107156787 cites W2593414960 @default.
• W3107156787 cites W2604909019 @default.
• W3107156787 cites W2609883120 @default.
• W3107156787 cites W2810554001 @default.
• W3107156787 cites W2886944874 @default.
• W3107156787 cites W2889061519 @default.
• W3107156787 cites W2897203992 @default.
• W3107156787 cites W2905536983 @default.
• W3107156787 cites W2910628332 @default.
• W3107156787 cites W2913483780 @default.
• W3107156787 cites W2934279571 @default.
• W3107156787 cites W2935854115 @default.
• W3107156787 cites W2942368658 @default.
• W3107156787 cites W2948647700 @default.
• W3107156787 cites W2949023359 @default.
• W3107156787 cites W2952813711 @default.
• W3107156787 cites W2959581809 @default.
• W3107156787 cites W2962804601 @default.
• W3107156787 cites W2962816904 @default.
• W3107156787 cites W2963265330 @default.
• W3107156787 cites W2963316641 @default.
• W3107156787 cites W2963412495 @default.
• W3107156787 cites W2963419596 @default.
• W3107156787 cites W2963488291 @default.
• W3107156787 cites W2963583471 @default.
• W3107156787 cites W2963591054 @default.
• W3107156787 cites W2963652981 @default.
• W3107156787 cites W2963654727 @default.
• W3107156787 cites W2963906250 @default.
• W3107156787 cites W2964677288 @default.
• W3107156787 cites W2964968086 @default.
• W3107156787 cites W2967043539 @default.
• W3107156787 cites W2968529893 @default.
• W3107156787 cites W2969365860 @default.
• W3107156787 cites W2970140852 @default.
• W3107156787 cites W2971028056 @default.
• W3107156787 cites W2981732213 @default.
• W3107156787 cites W2982014906 @default.
• W3107156787 cites W2982102242 @default.
• W3107156787 cites W2982535248 @default.
• W3107156787 cites W2983393775 @default.
• W3107156787 cites W2985775862 @default.
• W3107156787 cites W2995687155 @default.
• W3107156787 cites W3014263713 @default.
• W3107156787 cites W3034604951 @default.
• W3107156787 cites W4251147723 @default.
• W3107156787 doi "https://doi.org/10.1007/978-3-030-58565-5_35" @default.
• W3107156787 hasPublicationYear "2020" @default.
• W3107156787 type Work @default.
• W3107156787 sameAs 3107156787 @default.
• W3107156787 citedByCount "123" @default.
• W3107156787 countsByYear W31071567872019 @default.
• W3107156787 countsByYear W31071567872020 @default.
• W3107156787 countsByYear W31071567872021 @default.
• W3107156787 countsByYear W31071567872022 @default.
• W3107156787 countsByYear W31071567872023 @default.
• W3107156787 crossrefType "book-chapter" @default.
• W3107156787 hasAuthorship W3107156787A5002593702 @default.
• W3107156787 hasAuthorship W3107156787A5047354615 @default.
• W3107156787 hasAuthorship W3107156787A5083561103 @default.
• W3107156787 hasAuthorship W3107156787A5087307877 @default.
• W3107156787 hasBestOaLocation W31071567872 @default.
• W3107156787 hasConcept C115961682 @default.
• W3107156787 hasConcept C134306372 @default.
• W3107156787 hasConcept C136389625 @default.
• W3107156787 hasConcept C153180895 @default.
• W3107156787 hasConcept C154945302 @default.
• W3107156787 hasConcept C162324750 @default.
• W3107156787 hasConcept C187736073 @default.
• W3107156787 hasConcept C2780451532 @default.
• W3107156787 hasConcept C2781238097 @default.
• W3107156787 hasConcept C31972630 @default.
• W3107156787 hasConcept C33923547 @default.
• W3107156787 hasConcept C41008148 @default.
• W3107156787 hasConcept C50644808 @default.
• W3107156787 hasConcept C65909025 @default.

• next