Beauty in Details: HSE University and AIRI Scientists Develop a Method for High-Quality Image Editing
Researchers from the HSE AI Research Centre, AIRI, and the University of Bremen have developed a new image editing method based on deep learning—StyleFeatureEditor. This tool allows for precise reproduction of even the smallest details in an image while preserving them during the editing process. With its help, users can easily change hair colour or facial expressions without sacrificing image quality. The results of this three-party collaboration were published at the highly-cited computer vision conference CVPR 2024.
Artificial intelligence is already able to generate and edit images using generative adversarial networks (GANs). The architecture consists of two independent networks: a generator that creates images and a discriminator that distinguishes between real and generated samples. These networks compete with each other, and a new stage in their development is the StyleGAN model. This model can generate images and modify specific parts based on user requests, but it has not been able to work with real photos or images before.
Researchers from the HSE AI Research Centre, the Artificial Intelligence Research Institute (AIRI), and the University of Bremen have proposed a method to quickly and efficiently edit real images. This StyleFeatureEditor approach consists of two modules: the first inverts (reconstructs) the original image, and the second edits this reconstruction. The results of these two steps are passed to StyleGAN, which generates the edited image based on the internal representations. The developers addressed some challenges that had been encountered in previous research. With a small set of representations, the network could edit the image well, but it lost some details from the original. However, with a larger set, all the details were preserved, but the network had difficulty transforming them correctly according to the task.
To solve this, the researchers proposed a new solution: the first module finds both large and small representations, while the second learns how to edit the larger ones using the smaller ones as reference.
However, to train these modules to accurately edit the representations, the neural network requires both real images and their edited versions.
‘We needed examples, such as the same face with different expressions, hairstyles, and details. Unfortunately, such image pairs do not exist at the moment. So, we came up with a trick: using a method that works with small representations, we created a reconstruction of a real image and an example of editing this reconstruction. Although the examples were relatively simple and without details, the model clearly understood how to make the edits,’ explains Denis Bobkov, one of the authors of the article, a research intern at the Centre of Deep Learning and Bayesian Methods of the AI and Digital Science Institute (part of the HSE Faculty of Computer Science), and a Junior Research Fellow at AIRI’s Fusion Brain Lab.
However, training only on generated (simple) examples leads to a loss of detail when working with real (complex) images. To prevent this, the researchers added real images to the training dataset, and the neural network learnt to reconstruct them in detail.
Thus, by showing the model how to edit both simple and complex images, the scientists created conditions under which the network could edit complex images more effectively. In particular, the developed approach handles adding new elements of style while preserving the details of the original image better than other existing methods.
In the case of simple reconstruction (first row), StyleFeatureEditor accurately reproduced a hat, while most other methods almost completely lost it. The developed method showed the best results with additional accessories (third row): most methods could add glasses, but only the StyleFeatureEditor retained the original eye colour.
‘Thanks to this training technique on generated data, we have obtained a model with high editing quality and a fast processing speed due to the use of relatively lightweight neural networks. The StyleFeatureEditor framework requires only 0.07 seconds to edit a single image,’ says Aibek Alanov, Head of the Centre of Deep Learning and Bayesian Methods of the AI and Digital Science Institute (part of the HSE Faculty of Computer Science), and leader of the research group ‘Controlled Generative AI’ at AIRI's Fusion Brain Lab.
The research was funded by a grant from the Analytical Centre under the Government of the Russian Federation for AI research centres.
The research results will be presented at the Fall into ML 2024 conference on artificial intelligence and machine learning, which will take place at HSE University on October 25–26, 2024. Leading AI scientists will discuss the best papers published at top-tier (A*) flagship AI conferences in 2024. A demo of the developed method can be tried out on HuggingFace, and the source code is available on GitHub.
See also:
Educational Programmes on Robotics and Neural Network Technologies Launch at HSE University’s Faculty of Computer Science
Every year, in response to IT industry demands, the Higher School of Economics Faculty of Computer Science launches new educational programmes while updating existing ones. In 2026, the faculty introduced Bachelor’s and Master’s degree programmes in robotics for the first time.
Scientists Show That Peer Influence Can Be as Effective as Expert Advice
Eating habits can be shaped not only by the authority of medical experts but also through ordinary conversations among friends. Researchers at HSE University have shown that advice from peers to reduce sugar consumption is just as effective as advice from experts. The study's findings have been published in Frontiers in Nutrition.
HSE University Develops Tool for Assessing Text Complexity in Low-Resource Languages
Researchers at the HSE Centre for Language and Brain have developed a tool for assessing text complexity in low-resource languages. The first version supports several of Russia’s minority languages, including Adyghe, Bashkir, Buryat, Tatar, Ossetian, and Udmurt. This is the first tool of its kind designed specifically for these languages, taking into account their unique morphological and lexical features.
HSE Scientists Uncover How Authoritativeness Shapes Trust
Researchers at the HSE Institute for Cognitive Neuroscience have studied how the brain responds to audio deepfakes—realistic fake speech recordings created using AI. The study shows that people tend to trust the current opinion of an authoritative speaker even when new statements contradict the speaker’s previous position. This effect also occurs when the statement conflicts with the listener’s internal attitudes. The research has been published in the journal NeuroImage.
Language Mapping in the Operating Room: HSE Neurolinguists Assist Surgeons in Complex Brain Surgery
Researchers from the HSE Center for Language and Brain took part in brain surgery on a patient who had been seriously wounded in the SMO. A shell fragment approximately five centimetres long entered through the eye socket, penetrated the cranial cavity, and became lodged in the brain, piercing the temporal lobe responsible for language. Surgeons at the Burdenko Main Military Clinical Hospital removed the foreign object while the patient remained conscious. During the operation, neurolinguists conducted language tests to ensure that language function was preserved.
AI Overestimates How Smart People Are, According to HSE Economists
Scientists at HSE University have found that current AI models, including ChatGPT and Claude, tend to overestimate the rationality of their human opponents—whether first-year undergraduate students or experienced scientists—in strategic thinking games, such as the Keynesian beauty contest. While these models attempt to predict human behaviour, they often end up playing 'too smart' and losing because they assume a higher level of logic in people than is actually present. The study has been published in the Journal of Economic Behavior & Organization.
Scientists Discover One of the Longest-Lasting Cases of COVID-19
An international team, including researchers from HSE University, examined an unusual SARS-CoV-2 sample obtained from an HIV-positive patient. Genetic analysis revealed multiple mutations and showed that the virus had been evolving inside the patient’s body for two years. This finding supports the theory that the virus can persist in individuals for years, gradually accumulate mutations, and eventually spill back into the population. The study's findings have been published in Frontiers in Cellular and Infection Microbiology.
HSE Scientists Use MEG for Precise Language Mapping in the Brain
Scientists at the HSE Centre for Language and Brain have demonstrated a more accurate way to identify the boundaries of language regions in the brain. They used magnetoencephalography (MEG) together with a sentence-completion task, which activates language areas and reveals their functioning in real time. This approach can help clinicians plan surgeries more effectively and improve diagnostic accuracy in cases where fMRI is not the optimal method. The study has been published in the European Journal of Neuroscience.
For the First Time, Linguists Describe the History of Russian Sign Language Interpreter Training
A team of researchers from Russia and the United Kingdom has, for the first time, provided a detailed account of the emergence and evolution of the Russian Sign Language (RSL) interpreter training system. This large-scale study spans from the 19th century to the present day, revealing both the achievements and challenges faced by the professional community. Results have been published in The Routledge Handbook of Sign Language Translation and Interpreting.
HSE Scientists Develop DeepGQ: AI-based 'Google Maps' for G-Quadruplexes
Researchers at the HSE AI Research Centre have developed an AI model that opens up new possibilities for the diagnosis and treatment of serious diseases, including brain cancer and neurodegenerative disorders. Using artificial intelligence, the team studied G-quadruplexes—structures that play a crucial role in cellular function and in the development of organs and tissues. The findings have been published in Scientific Reports.