Matches in SemOpenAlex for { <https://semopenalex.org/work/W4289743511> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W4289743511 abstract "While recent deep monocular depth estimation approaches based on supervised regression have achieved remarkable performance, costly ground truth annotations are required during training. To cope with this issue, in this paper we present a novel unsupervised deep learning approach for predicting depth maps and show that the depth estimation task can be effectively tackled within an adversarial learning framework. Specifically, we propose a deep generative network that learns to predict the correspondence field i.e. the disparity map between two image views in a calibrated stereo camera setting. The proposed architecture consists of two generative sub-networks jointly trained with adversarial learning for reconstructing the disparity map and organized in a cycle such as to provide mutual constraints and supervision to each other. Extensive experiments on the publicly available datasets KITTI and Cityscapes demonstrate the effectiveness of the proposed model and competitive results with state of the art methods. The code and trained model are available on https://github.com/andrea-pilzer/unsup-stereo-depthGAN." @default.
- W4289743511 created "2022-08-04" @default.
- W4289743511 creator A5015741637 @default.
- W4289743511 creator A5027171279 @default.
- W4289743511 creator A5047852717 @default.
- W4289743511 creator A5053479862 @default.
- W4289743511 creator A5065059558 @default.
- W4289743511 date "2018-07-28" @default.
- W4289743511 modified "2023-09-26" @default.
- W4289743511 title "Unsupervised Adversarial Depth Estimation using Cycled Generative Networks" @default.
- W4289743511 doi "https://doi.org/10.48550/arxiv.1807.10915" @default.
- W4289743511 hasPublicationYear "2018" @default.
- W4289743511 type Work @default.
- W4289743511 citedByCount "0" @default.
- W4289743511 crossrefType "posted-content" @default.
- W4289743511 hasAuthorship W4289743511A5015741637 @default.
- W4289743511 hasAuthorship W4289743511A5027171279 @default.
- W4289743511 hasAuthorship W4289743511A5047852717 @default.
- W4289743511 hasAuthorship W4289743511A5053479862 @default.
- W4289743511 hasAuthorship W4289743511A5065059558 @default.
- W4289743511 hasBestOaLocation W42897435111 @default.
- W4289743511 hasConcept C108583219 @default.
- W4289743511 hasConcept C115961682 @default.
- W4289743511 hasConcept C119857082 @default.
- W4289743511 hasConcept C146849305 @default.
- W4289743511 hasConcept C153180895 @default.
- W4289743511 hasConcept C154945302 @default.
- W4289743511 hasConcept C162324750 @default.
- W4289743511 hasConcept C177264268 @default.
- W4289743511 hasConcept C187736073 @default.
- W4289743511 hasConcept C199360897 @default.
- W4289743511 hasConcept C202444582 @default.
- W4289743511 hasConcept C2776760102 @default.
- W4289743511 hasConcept C2780451532 @default.
- W4289743511 hasConcept C33923547 @default.
- W4289743511 hasConcept C37736160 @default.
- W4289743511 hasConcept C39890363 @default.
- W4289743511 hasConcept C41008148 @default.
- W4289743511 hasConcept C65909025 @default.
- W4289743511 hasConcept C8038995 @default.
- W4289743511 hasConcept C9652623 @default.
- W4289743511 hasConceptScore W4289743511C108583219 @default.
- W4289743511 hasConceptScore W4289743511C115961682 @default.
- W4289743511 hasConceptScore W4289743511C119857082 @default.
- W4289743511 hasConceptScore W4289743511C146849305 @default.
- W4289743511 hasConceptScore W4289743511C153180895 @default.
- W4289743511 hasConceptScore W4289743511C154945302 @default.
- W4289743511 hasConceptScore W4289743511C162324750 @default.
- W4289743511 hasConceptScore W4289743511C177264268 @default.
- W4289743511 hasConceptScore W4289743511C187736073 @default.
- W4289743511 hasConceptScore W4289743511C199360897 @default.
- W4289743511 hasConceptScore W4289743511C202444582 @default.
- W4289743511 hasConceptScore W4289743511C2776760102 @default.
- W4289743511 hasConceptScore W4289743511C2780451532 @default.
- W4289743511 hasConceptScore W4289743511C33923547 @default.
- W4289743511 hasConceptScore W4289743511C37736160 @default.
- W4289743511 hasConceptScore W4289743511C39890363 @default.
- W4289743511 hasConceptScore W4289743511C41008148 @default.
- W4289743511 hasConceptScore W4289743511C65909025 @default.
- W4289743511 hasConceptScore W4289743511C8038995 @default.
- W4289743511 hasConceptScore W4289743511C9652623 @default.
- W4289743511 hasLocation W42897435111 @default.
- W4289743511 hasOpenAccess W4289743511 @default.
- W4289743511 hasPrimaryLocation W42897435111 @default.
- W4289743511 hasRelatedWork W2884609081 @default.
- W4289743511 hasRelatedWork W3082895349 @default.
- W4289743511 hasRelatedWork W3123344745 @default.
- W4289743511 hasRelatedWork W3204711619 @default.
- W4289743511 hasRelatedWork W4211044943 @default.
- W4289743511 hasRelatedWork W4221136938 @default.
- W4289743511 hasRelatedWork W4289743511 @default.
- W4289743511 hasRelatedWork W4312831135 @default.
- W4289743511 hasRelatedWork W4379255972 @default.
- W4289743511 hasRelatedWork W3108696707 @default.
- W4289743511 isParatext "false" @default.
- W4289743511 isRetracted "false" @default.
- W4289743511 workType "article" @default.