FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313171699> ?p ?o ?g. }

• W4313171699 abstract "The majority of prior monocular depth estimation meth-ods without groundtruth depth guidance focus on driving scenarios. We show that such methods generalize poorly to unseen complex indoor scenes, where objects are cluttered and arbitrarily arranged in the near field. To obtain more robustness, we propose a structure distillation approach to learn knacks from an off-the-shelf relative depth estima-tor that produces structured but metric-agnostic depth. By combining structure distillation with a branch that learns metrics from left-right consistency, we attain structured and metric depth for generic indoor scenes and make inferences in real-time. To facilitate learning and evaluation, we col-lect SimSIN, a dataset from simulation with thousands of environments, and UniSIN, a dataset that contains about 500 real scan sequences of generic indoor environments. We experiment in both sim-to-real and real-to-real settings, and show improvements, as well as in downstream applications using our depth maps. This work provides a full study, covering methods, data, and applications aspects." @default.
• W4313171699 created "2023-01-06" @default.
• W4313171699 creator A5024267838 @default.
• W4313171699 creator A5033903130 @default.
• W4313171699 creator A5038297233 @default.
• W4313171699 creator A5051839223 @default.
• W4313171699 creator A5082235583 @default.
• W4313171699 date "2022-06-01" @default.
• W4313171699 modified "2023-10-13" @default.
• W4313171699 title "Toward Practical Monocular Indoor Depth Estimation" @default.
• W4313171699 cites W2017745767 @default.
• W4313171699 cites W2132947399 @default.
• W4313171699 cites W2150066425 @default.
• W4313171699 cites W2194775991 @default.
• W4313171699 cites W2340897893 @default.
• W4313171699 cites W2520707372 @default.
• W4313171699 cites W2902486335 @default.
• W4313171699 cites W2951730755 @default.
• W4313171699 cites W2962807621 @default.
• W4313171699 cites W2963591054 @default.
• W4313171699 cites W2963911235 @default.
• W4313171699 cites W2964014680 @default.
• W4313171699 cites W2964339842 @default.
• W4313171699 cites W2968826970 @default.
• W4313171699 cites W2981353488 @default.
• W4313171699 cites W2982102242 @default.
• W4313171699 cites W2982336692 @default.
• W4313171699 cites W2985775862 @default.
• W4313171699 cites W2990394353 @default.
• W4313171699 cites W3009020965 @default.
• W4313171699 cites W3022265613 @default.
• W4313171699 cites W3034475171 @default.
• W4313171699 cites W3034604951 @default.
• W4313171699 cites W3035056458 @default.
• W4313171699 cites W3048510980 @default.
• W4313171699 cites W3097660860 @default.
• W4313171699 cites W3100388886 @default.
• W4313171699 cites W3118942022 @default.
• W4313171699 cites W3130567435 @default.
• W4313171699 cites W3163232644 @default.
• W4313171699 cites W3171847116 @default.
• W4313171699 cites W3174211490 @default.
• W4313171699 cites W3174458495 @default.
• W4313171699 cites W3174541782 @default.
• W4313171699 cites W3175682855 @default.
• W4313171699 cites W3196148789 @default.
• W4313171699 cites W3203439539 @default.
• W4313171699 cites W4214520160 @default.
• W4313171699 cites W4214681287 @default.
• W4313171699 doi "https://doi.org/10.1109/cvpr52688.2022.00379" @default.
• W4313171699 hasPublicationYear "2022" @default.
• W4313171699 type Work @default.
• W4313171699 citedByCount "5" @default.
• W4313171699 countsByYear W43131716992023 @default.
• W4313171699 crossrefType "proceedings-article" @default.
• W4313171699 hasAuthorship W4313171699A5024267838 @default.
• W4313171699 hasAuthorship W4313171699A5033903130 @default.
• W4313171699 hasAuthorship W4313171699A5038297233 @default.
• W4313171699 hasAuthorship W4313171699A5051839223 @default.
• W4313171699 hasAuthorship W4313171699A5082235583 @default.
• W4313171699 hasBestOaLocation W43131716992 @default.
• W4313171699 hasConcept C104317684 @default.
• W4313171699 hasConcept C119857082 @default.
• W4313171699 hasConcept C120665830 @default.
• W4313171699 hasConcept C121332964 @default.
• W4313171699 hasConcept C154945302 @default.
• W4313171699 hasConcept C162324750 @default.
• W4313171699 hasConcept C176217482 @default.
• W4313171699 hasConcept C185592680 @default.
• W4313171699 hasConcept C192209626 @default.
• W4313171699 hasConcept C21547014 @default.
• W4313171699 hasConcept C2776436953 @default.
• W4313171699 hasConcept C31972630 @default.
• W4313171699 hasConcept C41008148 @default.
• W4313171699 hasConcept C55493867 @default.
• W4313171699 hasConcept C63479239 @default.
• W4313171699 hasConcept C65909025 @default.
• W4313171699 hasConceptScore W4313171699C104317684 @default.
• W4313171699 hasConceptScore W4313171699C119857082 @default.
• W4313171699 hasConceptScore W4313171699C120665830 @default.
• W4313171699 hasConceptScore W4313171699C121332964 @default.
• W4313171699 hasConceptScore W4313171699C154945302 @default.
• W4313171699 hasConceptScore W4313171699C162324750 @default.
• W4313171699 hasConceptScore W4313171699C176217482 @default.
• W4313171699 hasConceptScore W4313171699C185592680 @default.
• W4313171699 hasConceptScore W4313171699C192209626 @default.
• W4313171699 hasConceptScore W4313171699C21547014 @default.
• W4313171699 hasConceptScore W4313171699C2776436953 @default.
• W4313171699 hasConceptScore W4313171699C31972630 @default.
• W4313171699 hasConceptScore W4313171699C41008148 @default.
• W4313171699 hasConceptScore W4313171699C55493867 @default.
• W4313171699 hasConceptScore W4313171699C63479239 @default.
• W4313171699 hasConceptScore W4313171699C65909025 @default.
• W4313171699 hasLocation W43131716991 @default.
• W4313171699 hasLocation W43131716992 @default.
• W4313171699 hasOpenAccess W4313171699 @default.
• W4313171699 hasPrimaryLocation W43131716991 @default.
• W4313171699 hasRelatedWork W127013308 @default.
• W4313171699 hasRelatedWork W1628937209 @default.
• W4313171699 hasRelatedWork W2035976912 @default.

• next