FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2061563090> ?p ?o ?g. }

• W2061563090 abstract "We propose an edge based single image super-resolution algorithm.Our algorithm involves learning how ramp profiles transform across resolutions.Ramp profiles are defined as monotonic pixel profiles across edges.Our results demonstrate several advantages compared to other techniques. We propose the use of explicitly identified image structure to guide the solution of the single image super-resolution (SR) problem. We treat the image as a layout of homogeneous regions, surrounded by ramp edges of a larger contrast. Ramps are characterized by the property that any path through any ramp pixel, monotonically leading from one to the other side, has monotonically increasing (or decreasing) intensity values along it. Such a ramp profile thus captures the large contrast between the two homogeneous regions. In this paper, the SR problem is viewed primarily as one of super-resolving these ramps, since the relatively homogeneous interiors can be handled using simpler methods. Our approach involves learning how these ramps transform across resolutions, and applying the learnt transformations to the ramps of a test image. To obtain our final SR reconstruction, we use the transformed ramps as priors in a regularization framework, where the traditional backprojection constraint is used as the data term. As compared to conventional edge based SR methods, our approach provides three distinct advantages: (1) Conventional edge based SR methods are based on gradients, which use 2D filters with heuristically chosen parameters and these choices result in different gradient values. This sensitivity adversely affects learning gradient domain correspondences across different resolutions. We show that ramp profiles are more adaptive, stable and therefore reliable representations for learning edge transformations across resolutions. (2) Existing gradient based SR methods are often unable to sufficiently constrain the absolute brightness levels in the image. Our approach on the other hand, operates directly in the image intensity domain, enforcing sharpness as well as brightness consistency. (3) Unlike previous gradient based methods, we also explicitly incorporate dependency between closely spaced edges while learning ramp correspondences. This allows for better recovery of contrast across thin structures such as in high spatial frequency areas. We obtain results that are sharper and more faithful to the true image color, and show almost no ringing artifacts." @default.
• W2061563090 created "2016-06-24" @default.
• W2061563090 creator A5014161323 @default.
• W2061563090 creator A5055952568 @default.
• W2061563090 date "2015-06-01" @default.
• W2061563090 modified "2023-09-22" @default.
• W2061563090 title "Learning ramp transformation for single image super-resolution" @default.
• W2061563090 cites W1590078731 @default.
• W2061563090 cites W1976416062 @default.
• W2061563090 cites W1995228944 @default.
• W2061563090 cites W2049237558 @default.
• W2061563090 cites W2056370875 @default.
• W2061563090 cites W2061398022 @default.
• W2061563090 cites W2081385919 @default.
• W2061563090 cites W2087380704 @default.
• W2061563090 cites W2088254198 @default.
• W2061563090 cites W2097073572 @default.
• W2061563090 cites W2103106600 @default.
• W2061563090 cites W2111454493 @default.
• W2061563090 cites W2114398647 @default.
• W2061563090 cites W2118963448 @default.
• W2061563090 cites W2121058967 @default.
• W2061563090 cites W2124335859 @default.
• W2061563090 cites W2124378283 @default.
• W2061563090 cites W2127401436 @default.
• W2061563090 cites W2131349449 @default.
• W2061563090 cites W2131686571 @default.
• W2061563090 cites W2133665775 @default.
• W2061563090 cites W2139643804 @default.
• W2061563090 cites W2146640671 @default.
• W2061563090 cites W2146914716 @default.
• W2061563090 cites W2148450250 @default.
• W2061563090 cites W2149760002 @default.
• W2061563090 cites W2157231504 @default.
• W2061563090 cites W2161516371 @default.
• W2061563090 cites W2163935418 @default.
• W2061563090 cites W2172128189 @default.
• W2061563090 cites W2534320940 @default.
• W2061563090 cites W3137074406 @default.
• W2061563090 doi "https://doi.org/10.1016/j.cviu.2015.01.004" @default.
• W2061563090 hasPublicationYear "2015" @default.
• W2061563090 type Work @default.
• W2061563090 sameAs 2061563090 @default.
• W2061563090 citedByCount "3" @default.
• W2061563090 countsByYear W20615630902016 @default.
• W2061563090 countsByYear W20615630902018 @default.
• W2061563090 countsByYear W20615630902020 @default.
• W2061563090 crossrefType "journal-article" @default.
• W2061563090 hasAuthorship W2061563090A5014161323 @default.
• W2061563090 hasAuthorship W2061563090A5055952568 @default.
• W2061563090 hasConcept C104317684 @default.
• W2061563090 hasConcept C111472728 @default.
• W2061563090 hasConcept C11413529 @default.
• W2061563090 hasConcept C114614502 @default.
• W2061563090 hasConcept C115961682 @default.
• W2061563090 hasConcept C134306372 @default.
• W2061563090 hasConcept C138885662 @default.
• W2061563090 hasConcept C154945302 @default.
• W2061563090 hasConcept C160633673 @default.
• W2061563090 hasConcept C162307627 @default.
• W2061563090 hasConcept C185592680 @default.
• W2061563090 hasConcept C189950617 @default.
• W2061563090 hasConcept C204241405 @default.
• W2061563090 hasConcept C2776135515 @default.
• W2061563090 hasConcept C2776502983 @default.
• W2061563090 hasConcept C31972630 @default.
• W2061563090 hasConcept C33923547 @default.
• W2061563090 hasConcept C41008148 @default.
• W2061563090 hasConcept C55493867 @default.
• W2061563090 hasConcept C66882249 @default.
• W2061563090 hasConcept C72169020 @default.
• W2061563090 hasConceptScore W2061563090C104317684 @default.
• W2061563090 hasConceptScore W2061563090C111472728 @default.
• W2061563090 hasConceptScore W2061563090C11413529 @default.
• W2061563090 hasConceptScore W2061563090C114614502 @default.
• W2061563090 hasConceptScore W2061563090C115961682 @default.
• W2061563090 hasConceptScore W2061563090C134306372 @default.
• W2061563090 hasConceptScore W2061563090C138885662 @default.
• W2061563090 hasConceptScore W2061563090C154945302 @default.
• W2061563090 hasConceptScore W2061563090C160633673 @default.
• W2061563090 hasConceptScore W2061563090C162307627 @default.
• W2061563090 hasConceptScore W2061563090C185592680 @default.
• W2061563090 hasConceptScore W2061563090C189950617 @default.
• W2061563090 hasConceptScore W2061563090C204241405 @default.
• W2061563090 hasConceptScore W2061563090C2776135515 @default.
• W2061563090 hasConceptScore W2061563090C2776502983 @default.
• W2061563090 hasConceptScore W2061563090C31972630 @default.
• W2061563090 hasConceptScore W2061563090C33923547 @default.
• W2061563090 hasConceptScore W2061563090C41008148 @default.
• W2061563090 hasConceptScore W2061563090C55493867 @default.
• W2061563090 hasConceptScore W2061563090C66882249 @default.
• W2061563090 hasConceptScore W2061563090C72169020 @default.
• W2061563090 hasLocation W20615630901 @default.
• W2061563090 hasOpenAccess W2061563090 @default.
• W2061563090 hasPrimaryLocation W20615630901 @default.
• W2061563090 hasRelatedWork W1519053452 @default.
• W2061563090 hasRelatedWork W1524997166 @default.
• W2061563090 hasRelatedWork W1534008768 @default.
• W2061563090 hasRelatedWork W1559617278 @default.
• W2061563090 hasRelatedWork W185791870 @default.

• next