Evaluation on Video Super-Resolution via Self-Supervision-Guided Generative Adversarial Network with Image Denoising

  • Bo An Chen
  • , Li Wei Kang*
  • *Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Video super-resolution (VSR) is a technique used for generating high-resolution (HR) frames from the corresponding low-resolution (LR) frames.With the advancement in deep learning techniques and the popularity of high resolution display applications, VSR has drawn much attention in recent years.This paper presents an implementation and evaluation on the classical deep learning-based VSR framework, called TecoGAN (TEmporally COherent GAN), relying on learning temporal coherence via self-supervision for GAN (generative adversarial network)-based video generation.It has been found while applying VSR to enhance the video quality, possibly inherent noises within the frames would be enhanced simultaneously, resulting in unpleasing visual experience.To tackle this problem, we propose to integrate noise removal and VSR for obtaining the noise-removed HR video.Our improved VSR framework has been shown to outperform the original TecoGAN quantitatively and qualitatively.

Original languageEnglish
Title of host publicationInternational Workshop on Advanced Imaging Technology, IWAIT 2025
EditorsMasayuki Nakajima, Chuan-Yu Chang, Chia-Hung Yeh, Jae-Gon Kim, Kemao Qian, Phooi Yee Lau
PublisherSPIE
ISBN (Electronic)9781510688124
DOIs
Publication statusPublished - 2025
Event2025 International Workshop on Advanced Imaging Technology, IWAIT 2025 - Douliu City, Taiwan
Duration: 2025 Jan 62025 Jan 8

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume13510
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

Conference2025 International Workshop on Advanced Imaging Technology, IWAIT 2025
Country/TerritoryTaiwan
CityDouliu City
Period2025/01/062025/01/08

Keywords

  • deep learning
  • denoising
  • GAN
  • generative adversarial network
  • self-supervision
  • Video super-resolution

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Evaluation on Video Super-Resolution via Self-Supervision-Guided Generative Adversarial Network with Image Denoising'. Together they form a unique fingerprint.

Cite this