FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4311806083> ?p ?o ?g. }

• W4311806083 endingPage "10" @default.
• W4311806083 startingPage "1" @default.
• W4311806083 abstract "We tackle the problem of estimating correspondences from a general marker, such as a movie poster, to an image that captures such a marker. Conventionally, this problem is addressed by fitting a homography model based on sparse feature matching. However, they are only able to handle plane-like markers and the sparse features do not sufficiently utilize appearance information. In this paper, we propose a novel framework NeuralMarker, training a neural network estimating dense marker correspondences under various challenging conditions, such as marker deformation, harsh lighting, etc. Deep learning has presented an excellent performance in correspondence learning once provided with sufficient training data. However, annotating pixel-wise dense correspondence for training marker correspondence is too expensive. We observe that the challenges of marker correspondence estimation come from two individual aspects: geometry variation and appearance variation. We, therefore, design two components addressing these two challenges in NeuralMarker. First, we create a synthetic dataset FlyingMarkers containing marker-image pairs with ground truth dense correspondences. By training with FlyingMarkers, the neural network is encouraged to capture various marker motions. Second, we propose the novel Symmetric Epipolar Distance (SED) loss, which enables learning dense correspondence from posed images. Learning with the SED loss and the cross-lighting posed images collected by Structure-from-Motion (SfM), NeuralMarker is remarkably robust in harsh lighting environments and avoids synthetic image bias. Besides, we also propose a novel marker correspondence evaluation method circumstancing annotations on real marker-image pairs and create a new benchmark. We show that NeuralMarker significantly outperforms previous methods and enables new interesting applications, including Augmented Reality (AR) and video editing." @default.
• W4311806083 created "2022-12-28" @default.
• W4311806083 creator A5003458970 @default.
• W4311806083 creator A5023250570 @default.
• W4311806083 creator A5024134159 @default.
• W4311806083 creator A5037488807 @default.
• W4311806083 creator A5045816528 @default.
• W4311806083 creator A5052068936 @default.
• W4311806083 creator A5058813054 @default.
• W4311806083 creator A5065073978 @default.
• W4311806083 date "2022-11-30" @default.
• W4311806083 modified "2023-09-25" @default.
• W4311806083 title "NeuralMarker" @default.
• W4311806083 cites W1513100184 @default.
• W4311806083 cites W1588809898 @default.
• W4311806083 cites W1977194745 @default.
• W4311806083 cites W2029162082 @default.
• W4311806083 cites W2085261163 @default.
• W4311806083 cites W2103031616 @default.
• W4311806083 cites W2110321083 @default.
• W4311806083 cites W2115579991 @default.
• W4311806083 cites W2117064099 @default.
• W4311806083 cites W2125188427 @default.
• W4311806083 cites W2151103935 @default.
• W4311806083 cites W2163446794 @default.
• W4311806083 cites W2565233142 @default.
• W4311806083 cites W2604233003 @default.
• W4311806083 cites W2897093986 @default.
• W4311806083 cites W2963043350 @default.
• W4311806083 cites W2963542378 @default.
• W4311806083 cites W2963760790 @default.
• W4311806083 cites W2979458572 @default.
• W4311806083 cites W3034275286 @default.
• W4311806083 cites W3035477606 @default.
• W4311806083 cites W3043075211 @default.
• W4311806083 cites W3087047746 @default.
• W4311806083 cites W3100388886 @default.
• W4311806083 cites W3107540572 @default.
• W4311806083 cites W3109908659 @default.
• W4311806083 cites W3167674261 @default.
• W4311806083 cites W3184107870 @default.
• W4311806083 cites W4206610958 @default.
• W4311806083 cites W764651262 @default.
• W4311806083 doi "https://doi.org/10.1145/3550454.3555468" @default.
• W4311806083 hasPublicationYear "2022" @default.
• W4311806083 type Work @default.
• W4311806083 citedByCount "3" @default.
• W4311806083 countsByYear W43118060832023 @default.
• W4311806083 crossrefType "journal-article" @default.
• W4311806083 hasAuthorship W4311806083A5003458970 @default.
• W4311806083 hasAuthorship W4311806083A5023250570 @default.
• W4311806083 hasAuthorship W4311806083A5024134159 @default.
• W4311806083 hasAuthorship W4311806083A5037488807 @default.
• W4311806083 hasAuthorship W4311806083A5045816528 @default.
• W4311806083 hasAuthorship W4311806083A5052068936 @default.
• W4311806083 hasAuthorship W4311806083A5058813054 @default.
• W4311806083 hasAuthorship W4311806083A5065073978 @default.
• W4311806083 hasConcept C105795698 @default.
• W4311806083 hasConcept C115961682 @default.
• W4311806083 hasConcept C13280743 @default.
• W4311806083 hasConcept C138885662 @default.
• W4311806083 hasConcept C146849305 @default.
• W4311806083 hasConcept C153180895 @default.
• W4311806083 hasConcept C154945302 @default.
• W4311806083 hasConcept C177846678 @default.
• W4311806083 hasConcept C185798385 @default.
• W4311806083 hasConcept C205649164 @default.
• W4311806083 hasConcept C23379248 @default.
• W4311806083 hasConcept C2776401178 @default.
• W4311806083 hasConcept C28751775 @default.
• W4311806083 hasConcept C31972630 @default.
• W4311806083 hasConcept C33923547 @default.
• W4311806083 hasConcept C41008148 @default.
• W4311806083 hasConcept C41895202 @default.
• W4311806083 hasConcept C50644808 @default.
• W4311806083 hasConcept C75280867 @default.
• W4311806083 hasConceptScore W4311806083C105795698 @default.
• W4311806083 hasConceptScore W4311806083C115961682 @default.
• W4311806083 hasConceptScore W4311806083C13280743 @default.
• W4311806083 hasConceptScore W4311806083C138885662 @default.
• W4311806083 hasConceptScore W4311806083C146849305 @default.
• W4311806083 hasConceptScore W4311806083C153180895 @default.
• W4311806083 hasConceptScore W4311806083C154945302 @default.
• W4311806083 hasConceptScore W4311806083C177846678 @default.
• W4311806083 hasConceptScore W4311806083C185798385 @default.
• W4311806083 hasConceptScore W4311806083C205649164 @default.
• W4311806083 hasConceptScore W4311806083C23379248 @default.
• W4311806083 hasConceptScore W4311806083C2776401178 @default.
• W4311806083 hasConceptScore W4311806083C28751775 @default.
• W4311806083 hasConceptScore W4311806083C31972630 @default.
• W4311806083 hasConceptScore W4311806083C33923547 @default.
• W4311806083 hasConceptScore W4311806083C41008148 @default.
• W4311806083 hasConceptScore W4311806083C41895202 @default.
• W4311806083 hasConceptScore W4311806083C50644808 @default.
• W4311806083 hasConceptScore W4311806083C75280867 @default.
• W4311806083 hasIssue "6" @default.
• W4311806083 hasLocation W43118060831 @default.
• W4311806083 hasOpenAccess W4311806083 @default.

• next