Dimitris Ampeliotis

Alexandros Gkillas, Dimitris Ampeliotis, Kostas Berberidis

In recent literature there are plenty of works that combine handcrafted and learnable regularizers to solve inverse imaging problems. While this hybrid approach has demonstrated promising results, the motivation for combining handcrafted and learnable regularizers remains largely underexplored. This work aims to justify this combination, by demonstrating that the incorporation of proper handcrafted regularizers alongside learnable regularizers not only reduces the complexity of the learnable prior, but also the performance is notably enhanced. To analyze the impact of this synergy, we introduce the notion of residual structure, to refer to the structure of the solution that cannot be modeled by the handcrafted regularizers per se. Motivated by these, we propose a novel optimization framework for the hyperspectral deconvolution problem, called DeepMix. Based on the proposed optimization framework, an interpretable model is developed using the deep unrolling strategy, which consists of three distinct modules, namely, a data consistency module, a module that enforces the effect of the handcrafted regularizers, and a denoising module. Recognizing the collaborative nature of these modules, this work proposes a context aware denoising module designed to sustain the advancements achieved by the cooperative efforts of the other modules. This is facilitated through the incorporation of a proper skip connection, ensuring that essential details and structures identified by other modules are effectively retained and not lost during denoising. Extensive experimental results across simulated and real-world datasets demonstrate that DeepMix is notable for surpassing existing methodologies, offering marked improvements in both image quality and computational efficiency.

Sofia Iliopoulou, Dimitris Ampeliotis, Athanassios Skodras

Recent progress in learning-based image compression has demonstrated that end-to-end optimization can substantially outperform traditional codecs by jointly learning compact latent representations and probabilistic entropy models. However, many existing approaches achieve high rate-distortion efficiency at the expense of increased computational cost and limited parallelism. This paper presents ARCHE - Autoregressive Residual Compression with Hyperprior and Excitation, an end-to-end learned image compression framework that balances modeling accuracy and computational efficiency. The proposed architecture unifies hierarchical, spatial, and channel-based priors within a single probabilistic framework, capturing both global and local dependencies in the latent representation of the image, while employing adaptive feature recalibration and residual refinement to enhance latent representation quality. Without relying on recurrent or transformer-based components, ARCHE attains state-of-the-art rate-distortion efficiency: it reduces the BD-Rate by approximately 48% relative to the commonly used benchmark model of Balle et al., 30% relative to the channel-wise autoregressive model of Minnen & Singh and 5% against the VVC Intra codec on the Kodak benchmark dataset. The framework maintains computational efficiency with 95M parameters and 222ms running time per image. Visual comparisons confirm sharper textures and improved color fidelity, particularly at lower bit rates, demonstrating that accurate entropy modeling can be achieved through efficient convolutional designs suitable for practical deployment.

Alexandros Gkillas, Dimitris Ampeliotis, Kostas Berberidis

In this study the problem of Federated Learning (FL) is explored under a new perspective by utilizing the Deep Equilibrium (DEQ) models instead of conventional deep learning networks. We claim that incorporating DEQ models into the federated learning framework naturally addresses several open problems in FL, such as the communication overhead due to the sharing large models and the ability to incorporate heterogeneous edge devices with significantly different computation capabilities. Additionally, a weighted average fusion rule is proposed at the server-side of the FL framework to account for the different qualities of models from heterogeneous edge devices. To the best of our knowledge, this study is the first to establish a connection between DEQ models and federated learning, contributing to the development of an efficient and effective FL framework. Finally, promising initial experimental results are presented, demonstrating the potential of this approach in addressing challenges of FL.

Alexandros Gkillas, Dimitris Ampeliotis, Kostas Berberidis

In this study, the problem of computing a sparse representation of multi-dimensional visual data is considered. In general, such data e.g., hyperspectral images, color images or video data consists of signals that exhibit strong local dependencies. A new computationally efficient sparse coding optimization problem is derived by employing regularization terms that are adapted to the properties of the signals of interest. Exploiting the merits of the learnable regularization techniques, a neural network is employed to act as structure prior and reveal the underlying signal dependencies. To solve the optimization problem Deep unrolling and Deep equilibrium based algorithms are developed, forming highly interpretable and concise deep-learning-based architectures, that process the input dataset in a block-by-block fashion. Extensive simulation results, in the context of hyperspectral image denoising, are provided, which demonstrate that the proposed algorithms outperform significantly other sparse coding approaches and exhibit superior performance against recent state-of-the-art deep-learning-based denoising models. In a wider perspective, our work provides a unique bridge between a classic approach, that is the sparse representation theory, and modern representation tools that are based on deep learning modeling.