Daniela Ivanova

prof_pic.jpg

G141 Lilybank Gardens

Sir Alwyn Williams Building

University of Glasgow, G12 8RZ

Hi! I am currently a third-year Computing Science PhD student at the University of Glasgow. I am a part of the Computer Vision and Autonomous Systems (CVAS) research group and the Information, Data and Analysis (IDA) Section. My research focuses on developing machine learning approaches for the restoration of images captured on analogue media. I am currently supervised by Dr John Williamson and Dr Paul Henderson.

Prior to my PhD, I completed an Undergraduate degree in Computing Science at the University of Glasgow with Honours of the First Class. During that time, I developed an interest in Machine Learning and its applications in the fields of Natural Language Processing, Image Processing and Computer Vision. My final year project, “A Deep Learning approach to artefact correction in photographic film” combined those interests with my passion for analogue film photography, and served as a foundation for my PhD research proposal. Apart from that, I worked in large-format printing for two years during the start of my degree, and as a Full-stack developer (Golang & JavaScript) during my Honours.

news

Nov 22, 2023 Hosting the BMVC Doctoral Consortium today as part of the main BMVC conference in Aberdeen, Scotland!
Sep 29, 2023 “DiffInfinite: Large Mask-Image Synthesis via Parallel Random Patch Diffusion in Histopathology” accepted as a Spotlight paper at NeurIPS’23 Datasets & Benchmarks track! 🎉
Jan 31, 2023 “Simulating analog film damage to analyse and improve artifact restoration on high-resolution scans” accepted as a full paper at Eurographics’23! 🎉

selected publications

  1. visapp_gif.gif
    Perceptual Loss based Approach for Analogue Film Restoration
    Daniela Ivanova, Jan Siebert, and John Williamson
    Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, 2022
  2. eg.gif
    Simulating analogue film damage to analyse and improve artefact restoration on high-resolution scans
    Daniela IvanovaJohn Williamson, and Paul Henderson
    Computer Graphics Forum (Proceedings of Eurographics 2023), 2023
  3. diffinfinite.gif
    DiffInfinite: Large Mask-Image Synthesis via Parallel Random Patch Diffusion in Histopathology
    Marco Aversa, Gabriel Nobis, Miriam Hägele, Kai Standvoss, Mihaela Chirica, Roderick Murray-Smith, Ahmed Alaa, Lukas Ruff, Daniela Ivanova, Wojciech Samek, and 3 more authors
    Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks (NeurIPS), 2023