Dissertation/ Thesis
View in EDS

Low-level vision processing : new approaches and sensors

Bibliographic Details
Title: Low-level vision processing : new approaches and sensors
Authors: Wang, Zhouxia, 王州霞
Publisher Information: The University of Hong Kong (Pokfulam, Hong Kong)
Publication Year: 2023
Collection: University of Hong Kong: HKU Scholars Hub
Subject Terms: Image processing - Data processing
Description: Low-level Vision processing aims to pixel-wisely process low-quality vision data, such as images and videos, to attain their high-quality ones. Low-level vision processing is complex since it contains a wide variety of low-quality data and involves many scenarios. In this thesis, we study low-level vision processing in three kinds of scenarios: scenarios with human faces only, natural scenarios, and an extremely challenging scenario. For each scenario, we delicately design a corresponding approach according to the property of the unprocessed data and scenarios to attain high-quality processing results. Our studies of scenarios with human faces only mainly focus on blind face restoration. First, we propose a RestoreFormer++ for blind face image restoration. It introduces fully-spatial attention mechanisms to model the contextual information and the interplay with the priors, achieving high-quality face images with both realness and fidelity. Its priors are matched from a learned reconstruction-oriented high-quality dictionary which is more accordant to the face restoration task, leading to rich details in the restored face images. Moreover, it is more robust and general to real-world degradation since its well-designed extending degrading model alleviates the synthetic-to-real-world gap. Then, we extend our study to face video restoration. We systematically analyze the potential benefits and difficulties posed by current face image restoration algorithms when extended to real-world face video restoration and provide a viable solution to mitigate the analyzed difficulties. Our study of natural scenarios is image deblurring. In this work, we introduce an event-based vision sensor, which can detect per-pixel brightness changes in microsecond resolution. Considering the complementary between the intensity images captured with a frame-based camera and event data captured with an event camera in temporal and spatial aspects, we propose to alternately enhance the quality of intensity image and even data with a DeblurNet ...
Document Type: doctoral or postdoctoral thesis
Language: English
Relation: HKU Theses Online (HKUTO); 991044736606203414; https://hub.hku.hk/handle/10722/335162
Availability: https://hub.hku.hk/handle/10722/335162
Rights: The author retains all proprietary rights, (such as patent rights) and the right to use in future works. ; This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Accession Number: edsbas.C19E99BA
Database: BASE
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://hub.hku.hk/handle/10722/335162#
    Name: EDS - BASE (ns324271)
    Category: fullText
    Text: View record from BASE
Header DbId: edsbas
DbLabel: BASE
An: edsbas.C19E99BA
RelevancyScore: 851
AccessLevel: 3
PubType: Dissertation/ Thesis
PubTypeId: dissertation
PreciseRelevancyScore: 851.480346679688
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Low-level vision processing : new approaches and sensors
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Wang%2C+Zhouxia%22">Wang, Zhouxia</searchLink><br /><searchLink fieldCode="AR" term="%22王州霞%22">王州霞</searchLink>
– Name: Publisher
  Label: Publisher Information
  Group: PubInfo
  Data: The University of Hong Kong (Pokfulam, Hong Kong)
– Name: DatePubCY
  Label: Publication Year
  Group: Date
  Data: 2023
– Name: Subset
  Label: Collection
  Group: HoldingsInfo
  Data: University of Hong Kong: HKU Scholars Hub
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Image+processing+-+Data+processing%22">Image processing - Data processing</searchLink>
– Name: Abstract
  Label: Description
  Group: Ab
  Data: Low-level Vision processing aims to pixel-wisely process low-quality vision data, such as images and videos, to attain their high-quality ones. Low-level vision processing is complex since it contains a wide variety of low-quality data and involves many scenarios. In this thesis, we study low-level vision processing in three kinds of scenarios: scenarios with human faces only, natural scenarios, and an extremely challenging scenario. For each scenario, we delicately design a corresponding approach according to the property of the unprocessed data and scenarios to attain high-quality processing results. Our studies of scenarios with human faces only mainly focus on blind face restoration. First, we propose a RestoreFormer++ for blind face image restoration. It introduces fully-spatial attention mechanisms to model the contextual information and the interplay with the priors, achieving high-quality face images with both realness and fidelity. Its priors are matched from a learned reconstruction-oriented high-quality dictionary which is more accordant to the face restoration task, leading to rich details in the restored face images. Moreover, it is more robust and general to real-world degradation since its well-designed extending degrading model alleviates the synthetic-to-real-world gap. Then, we extend our study to face video restoration. We systematically analyze the potential benefits and difficulties posed by current face image restoration algorithms when extended to real-world face video restoration and provide a viable solution to mitigate the analyzed difficulties. Our study of natural scenarios is image deblurring. In this work, we introduce an event-based vision sensor, which can detect per-pixel brightness changes in microsecond resolution. Considering the complementary between the intensity images captured with a frame-based camera and event data captured with an event camera in temporal and spatial aspects, we propose to alternately enhance the quality of intensity image and even data with a DeblurNet ...
– Name: TypeDocument
  Label: Document Type
  Group: TypDoc
  Data: doctoral or postdoctoral thesis
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: NoteTitleSource
  Label: Relation
  Group: SrcInfo
  Data: HKU Theses Online (HKUTO); 991044736606203414; https://hub.hku.hk/handle/10722/335162
– Name: URL
  Label: Availability
  Group: URL
  Data: https://hub.hku.hk/handle/10722/335162
– Name: Copyright
  Label: Rights
  Group: Cpyrght
  Data: The author retains all proprietary rights, (such as patent rights) and the right to use in future works. ; This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
– Name: AN
  Label: Accession Number
  Group: ID
  Data: edsbas.C19E99BA
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsbas&AN=edsbas.C19E99BA
RecordInfo BibRecord:
  BibEntity:
    Languages:
      – Text: English
    Subjects:
      – SubjectFull: Image processing - Data processing
        Type: general
    Titles:
      – TitleFull: Low-level vision processing : new approaches and sensors
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Wang, Zhouxia
      – PersonEntity:
          Name:
            NameFull: 王州霞
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Type: published
              Y: 2023
          Identifiers:
            – Type: issn-locals
              Value: edsbas
            – Type: issn-locals
              Value: edsbas.oa
ResultId 1