S
Sotirios Papadopoulos
Researcher at Aristotle University of Thessaloniki
Publications - 3
Citations - 27
Sotirios Papadopoulos is an academic researcher from Aristotle University of Thessaloniki. The author has contributed to research in topics: Image segmentation & Deep learning. The author has an hindex of 2, co-authored 3 publications receiving 10 citations.
Papers
More filters
Journal ArticleDOI
Deep autoencoders for attribute preserving face de-identification
TL;DR: This paper presents various methods to finetune the encoder in both a supervised and unsupervised fashion to preserve facial attributes, while generating new faces which are both visually and quantitatively different from the original ones.
Proceedings ArticleDOI
Neural vision-based semantic 3D world modeling
TL;DR: In this article, a survey of state-of-the-art DNN-based methods for scene geometry estimation, image semantic segmentation and joint inference of both tasks is presented.
Proceedings ArticleDOI
Semantic Image Segmentation Guided By Scene Geometry
TL;DR: In this paper, a regularizer was proposed to penalize differences between semantic and self-supervised depth predictions on presumed object boundaries during CNN training, which does not resort to multitask training and does not require known or estimated depth maps during inference.