Skip to content
Menu
PyCon HK
  • Schedule
    • 2023
    • 2022
    • 2021
    • 2020 Fall
    • 2020 Spring
    • 2018
    • 2017
    • 2016
    • 2015
  • Sponsors
    • 2023
    • 2022
    • 2021
    • 2020 Fall
    • 2018
    • 2017
    • 2016
    • 2015
  • Organizers
    • Organizers
    • Volunteers
    • Booths
  • Supporting Organizations
  • Code of Conduct
    • Procedures for Reporting Incidents
    • Enforcement Procedures
  • About
    • PyCon HK
    • Conference Highlights
    • 2023
    • 2022
    • 2021
    • 2020 Fall
    • 2020 Spring
    • 2018
    • 2017
      • Photos
      • Videos
    • 2016
      • Photos
      • Videos
    • 2015
      • Photos
PyCon HK

Developments of Super Resolution

Posted on October 28, 2018September 18, 2024

Introduction of super resolution with deep learning techniques. Super resolution is a technique which serve low- resolution image as input and outputs high-resolution images. How to preserve edges and restore detail information in the high-resolution image is very important. In this talk, we will discuss the developments of super resolution, especially methods using deep learning where pytorch is used during training.

Buzzwords: Super resolution. deep learning. pytorch
Level: Beginner: Target audiences with basic experience of python programming
Requirements to Audiences: Basic knowledge in machine learning & Image processing.
Language: English

Speaker: GUAN Jingwei (Hong Kong)

Speaker Bio: Senior Engineer at TCL research HK/ Ph.D of The Chinese University of Hong Kong Speaker Photo:

GitHub: https://github.com/GUAN3737
LinkedIn: https://www.linkedin.com/in/jingwei-guan-aa6453130/
Website/Blog: http://www.ee.cuhk.edu.hk/~jwguan/

  • Instagram
  • LinkedIn
  • Facebook
  • Twitter
  • YouTube

Archives

©2025 PyCon HK | Powered by SuperbThemes!
← Heterogeneous Job processing with Apache Kafka ← Unlock the power of insurtech! A case study of digitizing the risk assessment in insurance using powerful python libraries and optimise performance with advanced machine learning models.