no code implementations • 19 Oct 2022 • Prodromos Boutis, Zisis Batzos, Konstantinos Konstantoudakis, Anastasios Dimou, Petros Daras
Nowadays, the need for large amounts of carefully and complexly annotated data for the training of computer vision modules continues to grow.
no code implementations • 18 Jul 2022 • DIMITRIOS KONSTANTINIDIS, Ilias Papastratis, Kosmas Dimitropoulos, Petros Daras
Vision Transformers are very popular nowadays due to their state-of-the-art performance in several computer vision tasks, such as image classification and action recognition.
Ranked #1 on Image Classification on Tiny-ImageNet (Top-1 Accuracy metric)
no code implementations • 11 Jul 2022 • Nikolaos Zioulis, Georgios Albanis, Petros Drakoulis, Federico Alvarez, Dimitrios Zarpalas, Petros Daras
In this work we introduce a biologically inspired long-range skip connection for the UNet architecture that relies on the perceptual illusion of hybrid images, being images that simultaneously encode two images.
no code implementations • 22 Jun 2022 • Nikolaos Zioulis, Federico Alvarez, Dimitrios Zarpalas, Petros Daras
Spherical cameras capture scenes in a holistic manner and have been used for room layout estimation.
3 code implementations • 13 Jun 2022 • Luca Gagliardi, Andrea Raffo, Ulderico Fugacci, Silvia Biasotti, Walter Rocchia, Hao Huang, Boulbaba Ben Amor, Yi Fang, Yuanyuan Zhang, Xiao Wang, Charles Christoffer, Daisuke Kihara, Apostolos Axenopoulos, Stelios Mylonas, Petros Daras
This paper presents the methods that have participated in the SHREC 2022 contest on protein-ligand binding site recognition.
1 code implementation • 1 Dec 2021 • Georgios Albanis, Nikolaos Zioulis, Petros Drakoulis, Federico Alvarez, Dimitrios Zarpalas, Petros Daras
In this work we contribute a distribution shift benchmark for a computer vision task; monocular depth estimation.
no code implementations • 19 Oct 2021 • Anargyros Chatzitofis, Nikolaos Zioulis, Georgios Nikolaos Albanis, Dimitrios Zarpalas, Petros Daras
A series of 2D (and 3D) keypoint estimation tasks are built upon heatmap coordinate representation, i. e. a probability map that allows for learnable and spatially aware encoding and decoding of keypoint coordinates on grids, even allowing for sub-pixel coordinate accuracy.
1 code implementation • 14 Oct 2021 • Anargyros Chatzitofis, Leonidas Saroglou, Prodromos Boutis, Petros Drakoulis, Nikolaos Zioulis, Shishir Subramanyam, Bart Kevelham, Caecilia Charbonnier, Pablo Cesar, Dimitrios Zarpalas, Stefanos Kollias, Petros Daras
HUMAN4D is introduced to the computer vision and graphics research communities to enable joint research on spatio-temporally aligned pose, volumetric, mRGBD and audio data cues.
1 code implementation • 14 Oct 2021 • Anargyros Chatzitofis, Dimitrios Zarpalas, Stefanos Kollias, Petros Daras
DeepMoCap explores motion capture by automatically localizing and labeling reflectors on depth images and, subsequently, on 3D space.
1 code implementation • 6 Sep 2021 • Georgios Albanis, Nikolaos Zioulis, Petros Drakoulis, Vasileios Gkitsas, Vladimiros Sterzentsenko, Federico Alvarez, Dimitrios Zarpalas, Petros Daras
Pano3D is a new benchmark for depth estimation from spherical panoramas.
no code implementations • Sensors 2021 • Ilias Papastratis, Kosmas Dimitropoulos, Petros Daras
The proposed network architecture consists of a generator that recognizes sign language glosses by extracting spatial and temporal features from video sequences, as well as a discriminator that evaluates the quality of the generator’s predictions by modeling text information at the sentence and gloss levels.
no code implementations • 9 Feb 2021 • Konstantinos Konstantoudakis, David Breitgand, Alexandros Doumanoglou, Nikolaos Zioulis, Avi Weit, Kyriaki Christaki, Petros Drakoulis, Emmanouil Christakis, Dimitrios Zarpalas, Petros Daras
Immersive 3D media is an emerging type of media that captures, encodes and reconstructs the 3D appearance of people and objects, with applications in tele-presence, teleconference, entertainment, gaming and other fields.
Networking and Internet Architecture Multimedia
1 code implementation • 7 Feb 2021 • Nikolaos Zioulis, Federico Alvarez, Dimitrios Zarpalas, Petros Daras
In this work we show how to estimate full room layouts in a single-shot, eliminating the need for postprocessing.
1 code implementation • RC 2020 • Georgios Nikolaos Albanis, Nikolaos Zioulis, Anargyros Chatzitofis, Anastasios Dimou, Dimitrios Zarpalas, Petros Daras
We communicated with the authors of [1] through GitHub, and we would like to thank them as they provided a fast and detailed response.
no code implementations • 19 Oct 2020 • Honglin Yuan, Remco C. Veltkamp, Georgios Albanis, Nikolaos Zioulis, Dimitrios Zarpalas, Petros Daras
From captured color and depth images, we use this simulator to generate a 3D dataset which has 400 photo-realistic synthesized color-and-depth image pairs with various view angles for training, and another 100 captured and synthetic images for testing.
1 code implementation • 10 Sep 2020 • Paschalis Bizopoulos, Nicholas Vretos, Petros Daras
In this paper, an extensive comparison of DL models for lung and COVID-19 lesion segmentation in Computerized Tomography (CT) scans is presented, which can also be used as a benchmark for testing medical image segmentation models.
2 code implementations • 20 Aug 2020 • Georgios Albanis, Nikolaos Zioulis, Anastasios Dimou, Dimitrios Zarpalas, Petros Daras
In this context, the 3D localisation of the UAV assistant is an important task that can facilitate the exchange of spatial information between the user and the UAV.
Ranked #1 on Drone Pose Estimation on UAVA
no code implementations • ECCV 2020 • Nikolas Adaloglou, Nicholas Vretos, Petros Daras
In this paper, a novel multi-view methodology for graph-based neural networks is proposed.
1 code implementation • 24 Jul 2020 • Nikolas Adaloglou, Theocharis Chatzis, Ilias Papastratis, Andreas Stergioulas, Georgios Th. Papadopoulos, Vassia Zacharopoulou, George J. Xydopoulos, Klimnis Atzakas, Dimitris Papazachariou, Petros Daras
In this paper, a comparative experimental assessment of computer vision-based methods for sign language recognition is conducted.
1 code implementation • 15 Jun 2020 • Christos Chatzikonstantinou, Georgios Th. Papadopoulos, Kosmas Dimitropoulos, Petros Daras
In this paper, the problem of pruning and compressingthe weights of various layers of deep neural networks is in-vestigated.
1 code implementation • 16 May 2020 • Vasileios Gkitsas, Nikolaos Zioulis, Federico Alvarez, Dimitrios Zarpalas, Petros Daras
We approach this problem differently, exploiting the availability of surface geometry to employ image-based relighting as a data generator and supervision mechanism.
no code implementations • 11 May 2020 • Ilias Papastratis, Kosmas Dimitropoulos, DIMITRIOS KONSTANTINIDIS, Petros Daras
The proposed method is trained jointly with video and text latent representations.
Ranked #10 on Sign Language Recognition on RWTH-PHOENIX-Weather 2014 T
no code implementations • 18 Apr 2020 • Spyridon Thermos, Petros Daras, Gerasimos Potamianos
In particular, we design an autoencoder that is trained using ground-truth labels of only the last frame of the sequence, and is able to infer pixel-wise affordance labels in both videos and static images.
2 code implementations • 23 Mar 2020 • Vladimiros Sterzentsenko, Alexandros Doumanoglou, Spyridon Thermos, Nikolaos Zioulis, Dimitrios Zarpalas, Petros Daras
This is accomplished by a soft, differentiable procrustes analysis that regularizes the segmentation and achieves higher extrinsic calibration performance in expanded sensor placement configurations, while being unrestricted by the number of sensors of the volumetric capture system.
2 code implementations • 13 Feb 2020 • Stelios K. Mylonas, Apostolos Axenopoulos, Petros Daras
The knowledge of potentially druggable binding sites on proteins is an important preliminary step towards the discovery of novel drugs.
no code implementations • 14 Nov 2019 • Kostas Loumponias, Nicholas Vretos, George Tsaklidis, Petros Daras
Firstly, the exact covariance matrix of the censored measurements is calculated by taking into account the censoring limits.
no code implementations • 24 Sep 2019 • Vasileios Gkitsas, Antonis Karakottas, Nikolaos Zioulis, Dimitrios Zarpalas, Petros Daras
Machine learning is driven by data, yet while their availability is constantly increasing, training data require laborious, time consuming and error-prone labelling or ground truth acquisition, which in some cases is very difficult or even impossible.
2 code implementations • 17 Sep 2019 • Nikolaos Zioulis, Antonis Karakottas, Dimitrios Zarpalas, Federico Alvarez, Petros Daras
This has led to the utilization of view synthesis as an indirect objective for learning depth estimation using efficient data acquisition procedures.
2 code implementations • 16 Sep 2019 • Antonis Karakottas, Nikolaos Zioulis, Stamatis Samaras, Dimitrios Ataloglou, Vasileios Gkitsas, Dimitrios Zarpalas, Petros Daras
We present a dataset of $360^o$ images of indoor spaces with their corresponding ground truth surface normal, and train a deep convolutional neural network (CNN) on the task of monocular 360 surface estimation.
1 code implementation • 3 Sep 2019 • Vladimiros Sterzentsenko, Antonis Karakottas, Alexandros Papachristou, Nikolaos Zioulis, Alexandros Doumanoglou, Dimitrios Zarpalas, Petros Daras
Multi-view capture systems are complex systems to engineer.
1 code implementation • ICCV 2019 • Vladimiros Sterzentsenko, Leonidas Saroglou, Anargyros Chatzitofis, Spyridon Thermos, Nikolaos Zioulis, Alexandros Doumanoglou, Dimitrios Zarpalas, Petros Daras
Specifically, the proposed autoencoder exploits multiple views of the same scene from different points of view in order to learn to suppress noise in a self-supervised end-to-end manner using depth and color information during training, yet only depth during inference.
no code implementations • 3 Dec 2018 • Panagiotis Stalidis, Theodoros Semertzidis, Petros Daras
In this paper, a detailed study on crime classification and prediction using deep learning architectures is presented.
1 code implementation • ECCV 2018 • Nikolaos Zioulis, Antonis Karakottas, Dimitrios Zarpalas, Petros Daras
Recent work on depth estimation up to now has only focused on projective images ignoring 360 content which is now increasingly and more easily produced.
Ranked #18 on Depth Estimation on Stanford2D3D Panoramic
no code implementations • 8 Dec 2017 • Dimitrios S. Alexiadis, Anargyros Chatzitofis, Nikolaos Zioulis, Olga Zoidi, Georgios Louizis, Dimitrios Zarpalas, Petros Daras, Senior Member, IEEE
The latest developments in 3D capturing, processing, and rendering provide means to unlock novel 3D application pathways.
no code implementations • ICCV 2017 • Georgios Zoumpourlis, Alexandros Doumanoglou, Nicholas Vretos, Petros Daras
However, while recent research results of neuroscience prove the existence of non-linear operations in the response of complex visual cells, little effort has been devoted to extend the convolution technique to non-linear forms.
no code implementations • CVPR 2017 • Spyridon Thermos, Georgios Th. Papadopoulos, Petros Daras, Gerasimos Potamianos
It is well-established by cognitive neuroscience that human perception of objects constitutes a complex process, where object appearance information is combined with evidence about the so-called object "affordances", namely the types of actions that humans typically perform when interacting with them.