Browsing by Author "Fudos, Ioannis"

Now showing 1 - 4 of 4
  • No Thumbnail Available
    Item
    Deep Terrain Expansion: Terrain Texture Synthesis with Deep Learning
    (The Eurographics Association, 2019) Toulatzis, Vasilis; Fudos, Ioannis; Vidal, Franck P. and Tam, Gary K. L. and Roberts, Jonathan C.
    In real-world applications terrains play a cardinal role in the field of games and geospatial applications such as Geographic Information Systems (GIS). The textures of a terrain are essential for creating virtual photorealistic environments for users. In many cases, the entire texture of a region is not available in high resolution or is much smaller than the required texture to cover a terrain. Tiling of a texture across a terrain or using an enlarged version of it usually fails to provide an acceptable photorealistic result. Consequently, high quality texture synthesis is a central issue in such settings. In this paper, we explore a novel methodology that extends previous work providing both synthesis and expansion/shrinkage of a texture.
  • No Thumbnail Available
    Item
    A Mesh Correspondence Approach for Efficient Animation Transfer
    (The Eurographics Association, 2019) Moutafidou, Anastasia; Fudos, Ioannis; Vidal, Franck P. and Tam, Gary K. L. and Roberts, Jonathan C.
    Animating a novel character not only needs a lot of effort and time but also requires the intervention of an experienced user. Moreover, the traditional animation pipeline for a set of characters can be a tedious and cumbersome process which often needs to be repeated several times to correct artifacts. We propose a user-friendly, semi-automated efficient method which is realized in two phases: (i) mesh correspondence, and (ii) skeleton and skinning transfer. We have developed a software tool for realizing the entire process without the need of third party software. We have improved the efficiency of the entire animation transfer process. To substantiate this, we provide a comparative performance evaluation with previous competent approaches.
  • Thumbnail Image
    Item
    Multiple Material Layer Visualization for Cultural Heritage Artifacts
    (The Eurographics Association, 2018) Moutafidou, Anastasia; Adamopoulos, Georgios; Drosou, Anastasios; Tzovaras, Dimitrios; Fudos, Ioannis; Sablatnig, Robert and Wimmer, Michael
    Material aging has a significant effect on the appearance of cultural heritage objects. These aging effects depend on material composition, object usage and weathering conditions but also on physical and chemical substance parameters. Some types of changes in the materials underneath the visible layers can also be detected and subsequently simulated. Furthermore, recent 3D printing technology enables exporting 3D objects with transparency information. We report on the development of software tools for visualization of material aging for artwork objects that can be used by curators and archaeologists to understand the nature of aging and prevent it with minimal preservation work.
  • Thumbnail Image
    Item
    A Real-time Voice Interface for Intelligent Wheelchairs
    (The Eurographics Association, 2023) Moschopoulos, Spyridon; Fudos, Ioannis; Koritsoglou, Kyriakos; Tatsis, Giorgos; Tzovaras, Dimitrios; Pelechano, Nuria; Liarokapis, Fotis; Rohmer, Damien; Asadipour, Ali
    This paper reports on the development of a real-time voice interface for navigation purposes of electric wheelchairs. To this end, we employ a convolutional neural network trained and fine-tuned using a small dataset that consists of Greek commands. Furthermore, the study explores a highly quantized version of the network to achieve computational efficiency while maintaining high accuracy on an edge device. The experimental results confirm the effectiveness of the model in accurately detecting keywords in real time with minimal misclassifications.