• 3D Face Reconstruction Based On a Single Input Image 

      Kwon, Yong Bin (Master thesis, 2021)
      Dette prosjektet har som mål å rekonstruere et 3D ansikt fra et bilde, noe som resulterer i en modell som ikke er påvirket av ansiktsvinkel eller lys. Dette er et viktig tema for forskjellige fagfelt innenfor datasyn---slik ...
    • 3D face tracking using Geometric Deep Learning 

      Stamland, Kristian (Master thesis, 2021)
      Fjessporing er et aktivt forskningsemne, spesielt etter at dyplæring og konvulsjons neurale nettverk kom på banen. Den aktive forskningen forholder seg for det meste til 2D bilder og videoer. Denne avhandlingen ser på ...
    • 3D Facial Reconstruction from Front and Side Images 

      Lium, Ola (Master thesis, 2020)
      Å kunne rekonstruere 3D modeller av ansikter fra 2D bilder er nyttig innenfor biometrisk ansiktsgjenkjenning. Nylige fremskritt innen datasyn og dyp læring har muliggjort bruk av nevralenettverk for å generere ...
    • Action unit detection in 3D facial videos with application in facial expression retrieval and recognition 

      Danelakis, Antonios; Theoharis, Theoharis; Pratikakis, Ioannis (Journal article; Peer reviewed, 2018)
      This work introduces a new scheme for action unit detection in 3D facial videos. Sets of features that define action unit activation in a robust manner are proposed. These features are computed based on eight detected ...
    • Cross-time registration of 3D point clouds 

      Saiti, Evdokia; Danelakis, Antonios; Theoharis, Theoharis (Peer reviewed; Journal article, 2021)
      Registration is a ubiquitous operation in visual computing and constitutes an important pre-processing step for operations such as 3D object reconstruction, retrieval and recognition. Particularly in cultural heritage (CH) ...
    • Effective Descriptors for Human Action Retrieval from 3D Mesh Sequences 

      Veinidis, Christos; Danelakis, Antonios; Pratikakis, Ioannis; Theoharis, Theoharis (Journal article; Peer reviewed, 2019)
      Two novel methods for fully unsupervised human action retrieval using 3D mesh sequences are presented. The first achieves high accuracy but is suitable for sequences consisting of clean meshes, such as artificial sequences ...
    • Image-based Somatotype as a Biometric Trait for Non-Collaborative Person Recognition at a Distance and On-The-Move 

      Danelakis, Antonios; Theoharis, Theoharis (Peer reviewed; Journal article, 2020)
      It has recently been shown in Re-Identification (Re-ID) work that full-body images of people reveal their somatotype, even after change in apparel. A significant advantage of this biometric trait is that it can easily be ...
    • Mesh-based 3D face recognition using Geometric Deep learning 

      Wardeberg, Håkon (Master thesis, 2021)
      Face recognition has been a very active and challenging task in the Computer Vision field. Performing face recognition based on facial images can be tricky since images are illumination, scale, and pose variant. On the ...
    • Robust 3D Face Reconstruction Using One/Two Facial Images 

      Lium, Ola; Kwon, Yong Bin; Danelakis, Antonios; Theoharis, Theoharis (Peer reviewed; Journal article, 2021)
      Being able to robustly reconstruct 3D faces from 2D images is a topic of pivotal importance for a variety of computer vision branches, such as face analysis and face recognition, whose applications are steadily growing. ...
    • Survey of automated multiple sclerosis lesion segmentation techniques on magnetic resonance imaging 

      Danelakis, Antonios; Theoharis, Theoharis; Verganelakis, Dimitrios A (Journal article; Peer reviewed, 2018)
      Multiple sclerosis (MS) is a chronic disease. It affects the central nervous system and its clinical manifestation can variate. Magnetic Resonance Imaging (MRI) is often used to detect, characterize and quantify MS lesions ...