Konstantinos Moustakas

Sarthak Pati, Ujjwal Baid, Brandon Edwards et al.

Although machine learning (ML) has shown promise in numerous domains, there are concerns about generalizability to out-of-sample data. This is currently addressed by centrally sharing ample, and importantly diverse, data from multiple sites. However, such centralization is challenging to scale (or even not feasible) due to various limitations. Federated ML (FL) provides an alternative to train accurate and generalizable ML models, by only sharing numerical model updates. Here we present findings from the largest FL study to-date, involving data from 71 healthcare institutions across 6 continents, to generate an automatic tumor boundary detector for the rare disease of glioblastoma, utilizing the largest dataset of such patients ever used in the literature (25,256 MRI scans from 6,314 patients). We demonstrate a 33% improvement over a publicly trained model to delineate the surgically targetable tumor, and 23% improvement over the tumor's entire extent. We anticipate our study to: 1) enable more studies in healthcare informed by large and diverse data, ensuring meaningful results for rare diseases and underrepresented populations, 2) facilitate further quantitative analyses for glioblastoma via performance optimization of our consensus model for eventual public release, and 3) demonstrate the effectiveness of FL at such scale and task complexity as a paradigm shift for multi-site collaborations, alleviating the need for data sharing.

Ilja Gubins, Marten L. Chaillet, Gijs van der Schot et al.

Cryo-electron tomography (cryo-ET) is an imaging technique that allows three-dimensional visualization of macro-molecular assemblies under near-native conditions. Cryo-ET comes with a number of challenges, mainly low signal-to-noise and inability to obtain images from all angles. Computational methods are key to analyze cryo-electron tomograms. To promote innovation in computational methods, we generate a novel simulated dataset to benchmark different methods of localization and classification of biological macromolecules in tomograms. Our publicly available dataset contains ten tomographic reconstructions of simulated cell-like volumes. Each volume contains twelve different types of complexes, varying in size, function and structure. In this paper, we have evaluated seven different methods of finding and classifying proteins. Seven research groups present results obtained with learning-based methods and trained on the simulated dataset, as well as a baseline template matching (TM), a traditional method widely used in cryo-ET research. We show that learning-based approaches can achieve notably better localization and classification performance than TM. We also experimentally confirm that there is a negative relationship between particle size and performance for all methods.

Nikos D. Fakotakis, Stavros Nousias, Gerasimos Arvanitis et al.

Asthma is a common, usually long-term respiratory disease with negative impact on global society and economy. Treatment involves using medical devices (inhalers) that distribute medication to the airways and its efficiency depends on the precision of the inhalation technique. There is a clinical need for objective methods to assess the inhalation technique, during clinical consultation. Integrated health monitoring systems, equipped with sensors, enable the recognition of drug actuation, embedded with sound signal detection, analysis and identification, from intelligent structures, that could provide powerful tools for reliable content management. Health monitoring systems equipped with sensors, embedded with sound signal detection, enable the recognition of drug actuation and could be used for effective audio content analysis. This paper revisits sound pattern recognition with machine learning techniques for asthma medication adherence assessment and presents the Respiratory and Drug Actuation (RDA) Suite (https://gitlab.com/vvr/monitoring-medication-adherence/rda-benchmark) for benchmarking and further research. The RDA Suite includes a set of tools for audio processing, feature extraction and classification procedures and is provided along with a dataset, consisting of respiratory and drug actuation sounds. The classification models in RDA are implemented based on conventional and advanced machine learning and deep networks' architectures. This study provides a comparative evaluation of the implemented approaches, examines potential improvements and discusses on challenges and future tendencies.

Ioannis Romanelis, Vlassios Fotis, Athanasios Kalogeras et al.

We propose a novel point cloud U-Net diffusion architecture for 3D generative modeling capable of generating high-quality and diverse 3D shapes while maintaining fast generation times. Our network employs a dual-branch architecture, combining the high-resolution representations of points with the computational efficiency of sparse voxels. Our fastest variant outperforms all non-diffusion generative approaches on unconditional shape generation, the most popular benchmark for evaluating point cloud generative models, while our largest model achieves state-of-the-art results among diffusion methods, with a runtime approximately 70% of the previously state-of-the-art PVD. Beyond unconditional generation, we perform extensive evaluations, including conditional generation on all categories of ShapeNet, demonstrating the scalability of our model to larger datasets, and implicit generation which allows our network to produce high quality point clouds on fewer timesteps, further decreasing the generation time. Finally, we evaluate the architecture's performance in point cloud completion and super-resolution. Our model excels in all tasks, establishing it as a state-of-the-art diffusion U-Net for point cloud generative modeling. The code is publicly available at https://github.com/JohnRomanelis/SPVD.git.

Ioannis Romanelis, Vlassis Fotis, Konstantinos Moustakas et al.

In this paper we delve into the properties of transformers, attained through self-supervision, in the point cloud domain. Specifically, we evaluate the effectiveness of Masked Autoencoding as a pretraining scheme, and explore Momentum Contrast as an alternative. In our study we investigate the impact of data quantity on the learned features, and uncover similarities in the transformer's behavior across domains. Through comprehensive visualiations, we observe that the transformer learns to attend to semantically meaningful regions, indicating that pretraining leads to a better understanding of the underlying geometry. Moreover, we examine the finetuning process and its effect on the learned representations. Based on that, we devise an unfreezing strategy which consistently outperforms our baseline without introducing any other modifications to the model or the training pipeline, and achieve state-of-the-art results in the classification task among transformer models.

Gerasimos Arvanitis, Nikolaos Stagakis, Evangelia I. Zacharaki et al.

Autonomous vehicles are expected to operate safely in real-life road conditions in the next years. Nevertheless, unanticipated events such as the existence of unexpected objects in the range of the road, can put safety at risk. The advancement of sensing and communication technologies and Internet of Things may facilitate the recognition of hazardous situations and information exchange in a cooperative driving scheme, providing new opportunities for the increase of collaborative situational awareness. Safe and unobtrusive visualization of the obtained information may nowadays be enabled through the adoption of novel Augmented Reality (AR) interfaces in the form of windshields. Motivated by these technological opportunities, we propose in this work a saliency-based distributed, cooperative obstacle detection and rendering scheme for increasing the driver's situational awareness through (i) automated obstacle detection, (ii) AR visualization and (iii) information sharing (upcoming potential dangers) with other connected vehicles or road infrastructure. An extensive evaluation study using a variety of real datasets for pothole detection showed that the proposed method provides favorable results and features compared to other recent and relevant approaches.

Iliana Loi, Konstantinos Moustakas

Investigating the impact of fatigue on human physiological function and motor behavior is crucial for developing biomechanics and medical applications aimed at mitigating fatigue, reducing injury risk, and creating sophisticated ergonomic designs, as well as for producing physically-plausible 3D animation sequences. While the former has a prominent position in state-of-the-art literature, fatigue-driven motion generation is still an underexplored area. In this study, we present FatigueFusion, a deep-learning architecture for the fusion of fatigue features within a latent representation space, enabling the creation of a variation of novel fatigued movements, intermediate fatigued states, and progressively fatigued motions. Unlike existing approaches that focus on imitating the effects of fatigue accumulation in motion patterns, our framework incorporates algorithmic and data-driven modules to impose subject-specific temporal and spatial fatigue features on nonfatigued motions, while leveraging PINN-based techniques to simulate fatigue intensity. Since all motion modulation tasks are taking place in latent space, FatigueFusion offers an end-to-end architecture that operates directly on non-fatigued joint angle sequences and control parameters, allowing seamless integration into any motion synthesis pipeline, without relying on fatigue input data. Overall, our framework can be employed for various fatigue-driven synthesis tasks, such as fatigue profile transfer and fusion, while it also provides a solution for accurate rendering of the human fatigue state in both animation and simulation pipelines.

Iliana Loi, Konstantinos Moustakas

Fatigue modeling is essential for motion synthesis tasks to model human motions under fatigued conditions and biomechanical engineering applications, such as investigating the variations in movement patterns and posture due to fatigue, defining injury risk mitigation and prevention strategies, formulating fatigue minimization schemes and creating improved ergonomic designs. Nevertheless, employing data-driven methods for synthesizing the impact of fatigue on motion, receives little to no attention in the literature. In this work, we present Fatigue-PINN, a deep learning framework based on Physics-Informed Neural Networks, for modeling fatigued human movements, while providing joint-specific fatigue configurations for adaptation and mitigation of motion artifacts on a joint level, resulting in more realistic animations. To account for muscle fatigue, we simulate the fatigue-induced fluctuations in the maximum exerted joint torques by leveraging a PINN adaptation of the Three-Compartment Controller model to exploit physics-domain knowledge for improving accuracy. This model also introduces parametric motion alignment with respect to joint-specific fatigue, hence avoiding sharp frame transitions. Our results indicate that Fatigue-PINN accurately simulates the effects of externally perceived fatigue on open-type human movements being consistent with findings from real-world experimental fatigue studies. Since fatigue is incorporated in torque space, Fatigue-PINN provides an end-to-end encoder-decoder-like architecture, to ensure transforming joint angles to joint torques and vice-versa, thus, being compatible with motion synthesis frameworks operating on joint angles.

Nikolaos Chandrinos, Iliana Loi, Panagiotis Zachos et al.

Artificial intelligence, machine learning, and deep learning as a service have become the status quo for many industries, leading to the widespread deployment of models that handle sensitive data. Well-performing models, the industry seeks, usually rely on a large volume of training data. However, the use of such data raises serious privacy concerns due to the potential risks of leaks of highly sensitive information. One prominent threat is the Membership Inference Attack, where adversaries attempt to deduce whether a specific data point was used in a model's training process. An adversary's ability to determine an individual's presence represents a significant privacy threat, especially when related to a group of users sharing sensitive information. Hence, well-designed privacy-preserving machine learning solutions are critically needed in the industry. In this work, we compare the effectiveness of L2 regularization and differential privacy in mitigating Membership Inference Attack risks. Even though regularization techniques like L2 regularization are commonly employed to reduce overfitting, a condition that enhances the effectiveness of Membership Inference Attacks, their impact on mitigating these attacks has not been systematically explored.

Vlassis Fotis, Ioannis Romanelis, Georgios Mylonas et al.

In this paper we study the problem of shape part retrieval in the point cloud domain. Shape retrieval methods in the literature rely on the presence of an existing query object, but what if the part we are looking for is not available? We present Part Retrieval Pipeline (PReP), a pipeline that creatively utilizes metric learning techniques along with a trained classification model to measure the suitability of potential replacement parts from a database, as part of an application scenario targeting circular economy. Through an innovative training procedure with increasing difficulty, it is able to learn to recognize suitable parts relying only on shape context. Thanks to its low parameter size and computational requirements, it can be used to sort through a warehouse of potentially tens of thousand of spare parts in just a few seconds. We also establish an alternative baseline approach to compare against, and extensively document the unique challenges associated with this task, as well as identify the design choices to solve them.

Stavros Nousias, Gerasimos Arvanitis, Aris S. Lalos et al.

Recent advances in 3D scanning technology have enabled the deployment of 3D models in various industrial applications like digital twins, remote inspection and reverse engineering. Despite their evolving performance, 3D scanners, still introduce noise and artifacts in the acquired dense models. In this work, we propose a fast and robust denoising method for dense 3D scanned industrial models. The proposed approach employs conditional variational autoencoders to effectively filter face normals. Training and inference are performed in a sliding patch setup reducing the size of the required training data and execution times. We conducted extensive evaluation studies using 3D scanned and CAD models. The results verify plausible denoising outcomes, demonstrating similar or higher reconstruction accuracy, compared to other state-of-the-art approaches. Specifically, for 3D models with more than 1e4 faces, the presented pipeline is twice as fast as methods with equivalent reconstruction error.

Dimitrios Chamzas, Constantinos Chamzas, Konstantinos Moustakas

During the last years, the emerging field of Augmented & Virtual Reality (AR-VR) has seen tremendousgrowth. At the same time there is a trend to develop low cost high-quality AR systems where computing poweris in demand. Feature points are extensively used in these real-time frame-rate and 3D applications, thereforeefficient high-speed feature detectors are necessary. Corners are such special features and often are used as thefirst step in the marker alignment in Augmented Reality (AR). Corners are also used in image registration andrecognition, tracking, SLAM, robot path finding and 2D or 3D object detection and retrieval. Therefore thereis a large number of corner detection algorithms but most of them are too computationally intensive for use inreal-time applications of any complexity. Many times the border of the image is a convex polygon. For thisspecial, but quite common case, we have developed a specific algorithm, cMinMax. The proposed algorithmis faster, approximately by a factor of 5 compared to the widely used Harris Corner Detection algorithm. Inaddition is highly parallelizable. The algorithm is suitable for the fast registration of markers in augmentedreality systems and in applications where a computationally efficient real time feature detector is necessary.The algorithm can also be extended to N-dimensional polyhedrons.

Dimitrios Chamzas, Konstantinos Moustakas

During the last years, the emerging field of Augmented and Virtual Reality (AR-VR) has seen tremendous growth. An interface that has also become very popular for the AR systems is the tangible interface or passive-haptic interface. Specifically, an interface where users can manipulate digital information with input devices that are physical objects. This work presents a low cost Augmented Reality system with a tangible interface that offers interaction between the real and the virtual world. The system estimates in real-time the 3D position of a small colored ball (input device), it maps it to the 3D virtual world and then uses it to control the AR application that runs in a mobile device. Using the 3D position of our "input" device, it allows us to implement more complicated interactivity compared to a 2D input device. Finally, we present a simple, fast and robust algorithm that can estimate the corners of a convex quadrangle. The proposed algorithm is suitable for the fast registration of markers and significantly improves performance compared to the state of the art.