Search

3D face reconstruction from a single image is a task that has garnered increased interest in the Computer Vision community, especially due to its broad use in a number of applications such as realistic 3D avatar creation, pose invariant face recognition and face hallucination. Since the introduction of the 3D Morphable Model in the late 90's, we witnessed an explosion of research aiming at particularly tackling this task. Nevertheless, despite the increasing level of detail in the 3D face reconstructions from single images mainly attributed to deep learning advances, finer and highly deformable components of the face such as the tongue are still absent from all 3D face models in the literature, although being very important for the realness of the 3D avatar representations. In this work we present the first, to the best of our knowledge, end-to-end trainable pipeline that accurately reconstructs the 3D face together with the tongue. Moreover, we make this pipeline robust in "in-the-wild" images by introducing a novel GAN method tailored for 3D tongue surface generation. Finally, we make publicly available to the community the first diverse tongue dataset, consisting of 1,800 raw scans of 700 individuals varying in gender, age, and ethnicity backgrounds. As we demonstrate in an extensive series of quantitative as well as qualitative experiments, our model proves to be robust and realistically captures the 3D tongue structure, even in adverse "in-the-wild" conditions., Comment: 10 pages, 9 figures

Introduction: The identification of occult sources of infection is of paramount importance to improve the outcomes of patients with sepsis. Aim: The investigation of the clinical impact of computed tomography (CT) scans in patients with sepsis of unknown origin. Methods: A systematic review of studies published up to December 2016 in PubMed and Scopus databases was conducted, with the following key-words: “'sepsis”, “severe sepsis”, “septic shock”, “unknown origin”, “computed tomography” and “CT”. The keywords were searched in the title and abstract of the studies, while the filters "human" and "English language" were used. The inclusion criteria in this review were: studies should concern patients sepsis or severe sepsis or septic shock of unknown origin, as well as patients having undergone CT or positron emission tomography (PET/CT). Results: Of the published studies, 5 met the inclusion criteria. The results of the studies showed that in all of the 75 and 89 patients underwent PET/CT and CT, true positive findings showed in 50 (66.66%) and in 29 (35%) patients, respectively, while in 23 out of 50 (46%) and in all of the 29 (100%) patients, findings led to the selection of the appropriate therapeutic intervention or led to a change in the initial chosen treatment. Conclusions: CT and PET/CT are valuable tools in identifying occult sources of infection in patients with sepsis or severe sepsis or septic shock, contributing to the selection of the appropriate therapeutic intervention and leading to higher rates of survival.