Eleftherios Ioannou

I hold a PhD in Computer Science from the University of Sheffield where I have been a member of the Computer Vision Research Group.
My research has explored artistic style transfer, the process of transferring the style of one image onto an input image, video or game. My expertise lies at the intersection of computer vision, computer graphics, and image processing with a growing interest for their application in biology.

Currently, I work as a Research Associate at the School of Biosciences, exploring deep learning-based approaches for extracting and analysing colour pattern information from biological images. My work aims to empower researchers by enabling the characterisation of colour pattern phenotypes from diverse image datasets, bridging the gap between computational techniques and biological understanding.

eioannou06 [at] gmail.com

Scholar  /  Github  /  Medium

ioannoue.alphaxiv.io

Current Projects

Adopting a cutting-edge hierarchical semantic segmentation strategy to develop models that are capable of accurately detecting not only a specimen within an image but also of simultaneously segmenting regions within the specimen. Developing a powerful workflow for colour pattern analysis that leverages contrastive learning.

A trandisciplinary multimodal research project in collaboration with Shameru Collective. Combining arts and sciences to explore public health heritate and what lessons can be drawn for application today.

Developing a finetuned LLM for malaria-related text and image analysis and creating a 3D avatar of Mehmet Aziz, the person who helped eradicate malaria in Cyprus.

Publications

My research explores the utilization of depth and other data for the improvement of the quality of artistic style transfer models.

We introduce a new, highly controlled synthetic dataset that encompasses the essential attributes required for analyzing OoD behavior.

We use a perceptual quality-guided knowledge distillation framework and train a compressed model inspired by work in image quality assessment of 3D renderings, which substantially reduces both memory usage and processing time with limited impact on stylisation quality.

We provide an in-depth analysis of existing evaluation techniques, identify the inconsistencies and limitations of current evaluation methods, and give recommendations for standardised evaluation practices.

Utilizing G-buffer data enables the stylization process to be more aware of the geometric and semantic aspects of a game scene. G-buffer information utilized during inference time improves the stability of the stylizations, and offers a controllable way to stylize computer games.

We inject depth-aware NST as part of the 3D rendering pipeline.

A depth encoder network encodes ground-truth depth information which is fused into the stylization network. We employ ConvLSTM layers in the encoder, and a design a loss function based on calculated depth.

Empower teacher education using a novel Virtual Reality (VR) based approach. Development made in Unity.

Our approach uses a deep residual convolutional network with instance normalization layers that utilizes an advanced depth prediction network to integrate depth preservation as an additional loss function to content and style.

We support the systematic exploration of landscape archaeology through time, from prehistory to today, through the design and development of an Augmented Reality (AR) application.

We present an AR art app, running in real time on a smartphone, that can be used to bring to life inanimate objects such as statues.

The project produced Augmented Reality (AR) software that allows the users to view the stones standing and interact with them in situ.

Miscellanea

• After Malaria: Animated Exchanges in Health Heritage
• cloud.torrent installation at the BufferFringe 2023
• Senrosial Entrapment Artistic installation at the Youth Makerspace

• Arcane: The Art Within The Art
• A Tribute to AI Art
• On Tokens
• Neural Style Transfer: Past, present, future
• Semantic Segmentation of Water Bodies in Images
• Football 3.0: The beautiful game in the age of Artificial Intelligence
• Diffusion: The Physics principle behind the success of Modern AI Art

Code stolen from jonbarron/jonbarron_website.