Matches in SemOpenAlex for { <https://semopenalex.org/work/W4292960520> ?p ?o ?g. }
Showing items 1 to 65 of
65
with 100 items per page.
- W4292960520 abstract "Blind image deblurring (BID) has been extensively studied in computer vision and adjacent fields. Modern methods for BID can be grouped into two categories: single-instance methods that deal with individual instances using statistical inference and numerical optimization, and data-driven methods that train deep-learning models to deblur future instances directly. Data-driven methods can be free from the difficulty in deriving accurate blur models, but are fundamentally limited by the diversity and quality of the training data -- collecting sufficiently expressive and realistic training data is a standing challenge. In this paper, we focus on single-instance methods that remain competitive and indispensable. However, most such methods do not prescribe how to deal with unknown kernel size and substantial noise, precluding practical deployment. Indeed, we show that several state-of-the-art (SOTA) single-instance methods are unstable when the kernel size is overspecified, and/or the noise level is high. On the positive side, we propose a practical BID method that is stable against both, the first of its kind. Our method builds on the recent ideas of solving inverse problems by integrating the physical models and structured deep neural networks, without extra training data. We introduce several crucial modifications to achieve the desired stability. Extensive empirical tests on standard synthetic datasets, as well as real-world NTIRE2020 and RealBlur datasets, show the superior effectiveness and practicality of our BID method compared to SOTA single-instance as well as data-driven methods. The code of our method is available at: url{https://github.com/sun-umn/Blind-Image-Deblurring}." @default.
- W4292960520 created "2022-08-24" @default.
- W4292960520 creator A5021269788 @default.
- W4292960520 creator A5035240743 @default.
- W4292960520 creator A5075755051 @default.
- W4292960520 creator A5085574874 @default.
- W4292960520 date "2022-08-18" @default.
- W4292960520 modified "2023-10-18" @default.
- W4292960520 title "Blind Image Deblurring with Unknown Kernel Size and Substantial Noise" @default.
- W4292960520 doi "https://doi.org/10.1007/s11263-023-01883-x" @default.
- W4292960520 hasPublicationYear "2022" @default.
- W4292960520 type Work @default.
- W4292960520 citedByCount "0" @default.
- W4292960520 crossrefType "posted-content" @default.
- W4292960520 hasAuthorship W4292960520A5021269788 @default.
- W4292960520 hasAuthorship W4292960520A5035240743 @default.
- W4292960520 hasAuthorship W4292960520A5075755051 @default.
- W4292960520 hasAuthorship W4292960520A5085574874 @default.
- W4292960520 hasBestOaLocation W42929605201 @default.
- W4292960520 hasConcept C106430172 @default.
- W4292960520 hasConcept C108583219 @default.
- W4292960520 hasConcept C112972136 @default.
- W4292960520 hasConcept C114614502 @default.
- W4292960520 hasConcept C115961682 @default.
- W4292960520 hasConcept C119857082 @default.
- W4292960520 hasConcept C124101348 @default.
- W4292960520 hasConcept C154945302 @default.
- W4292960520 hasConcept C2776214188 @default.
- W4292960520 hasConcept C2777693668 @default.
- W4292960520 hasConcept C33923547 @default.
- W4292960520 hasConcept C41008148 @default.
- W4292960520 hasConcept C74193536 @default.
- W4292960520 hasConcept C9417928 @default.
- W4292960520 hasConcept C99498987 @default.
- W4292960520 hasConceptScore W4292960520C106430172 @default.
- W4292960520 hasConceptScore W4292960520C108583219 @default.
- W4292960520 hasConceptScore W4292960520C112972136 @default.
- W4292960520 hasConceptScore W4292960520C114614502 @default.
- W4292960520 hasConceptScore W4292960520C115961682 @default.
- W4292960520 hasConceptScore W4292960520C119857082 @default.
- W4292960520 hasConceptScore W4292960520C124101348 @default.
- W4292960520 hasConceptScore W4292960520C154945302 @default.
- W4292960520 hasConceptScore W4292960520C2776214188 @default.
- W4292960520 hasConceptScore W4292960520C2777693668 @default.
- W4292960520 hasConceptScore W4292960520C33923547 @default.
- W4292960520 hasConceptScore W4292960520C41008148 @default.
- W4292960520 hasConceptScore W4292960520C74193536 @default.
- W4292960520 hasConceptScore W4292960520C9417928 @default.
- W4292960520 hasConceptScore W4292960520C99498987 @default.
- W4292960520 hasLocation W42929605201 @default.
- W4292960520 hasOpenAccess W4292960520 @default.
- W4292960520 hasPrimaryLocation W42929605201 @default.
- W4292960520 hasRelatedWork W1993928981 @default.
- W4292960520 hasRelatedWork W2060018053 @default.
- W4292960520 hasRelatedWork W3023581765 @default.
- W4292960520 hasRelatedWork W4223943233 @default.
- W4292960520 hasRelatedWork W4225161397 @default.
- W4292960520 hasRelatedWork W4312200629 @default.
- W4292960520 hasRelatedWork W4360585206 @default.
- W4292960520 hasRelatedWork W4364306694 @default.
- W4292960520 hasRelatedWork W4380075502 @default.
- W4292960520 hasRelatedWork W4380086463 @default.
- W4292960520 isParatext "false" @default.
- W4292960520 isRetracted "false" @default.
- W4292960520 workType "article" @default.