Adult2Child Age Regression Using CycleGANs

Thomas Domas, Yuzhu Dong, Brendan John, Ariel Shamir, Andreas Aristidou, Eakta Jain

Presented at: ACM Symposium on Applied Perception (SAP'19), Barcelona, Spain, Sep 2019

paper bibtex

Real-time 3D Human Pose and Motion Reconstruction from Monocular RGB Videos

Anastasios Yiannakides, Andreas Aristidou, Yiorgos Chrysanthou

Comp. Animation & Virtual Worlds, 30(3-4), May 2019

Presented at: Computer Animation and Social Agents - CASA'19

In this paper, we present a method that reconstructs articulated human motion, taken from a monocular RGB camera. Our method fits 2D deep estimated poses of multiple characters, with the 2D multi-view joint projections of 3D motion data, to retrieve the 3D body pose of the tracked character. By taking into consideration the temporal consistency of motion, it generates natural and smooth animations, in real-time, without bone length violations.

DOI paper video bibtex project page

Automatic Environment Map Registration

Ulysse Larvy, Celine Loscos, Yiorgos Chrysanthou

Presented at: Eurographics Short Papers, Jan 2019

DOI paper

Deep Motifs and Motion Signatures

Andreas Aristidou, Daniel Cohen-Or, Jessica K. Hodgins, Yiorgos Chrysanthou, Ariel Shamir

ACM Transaction on Graphics, 37(6), Article 187, 2018, Dec 2018

Presented at: SIGGRAPH Asia 2018

We introduce deep motion signatures, which are time-scale and temporal-order invariant, offering a succinct and descriptive representation of motion sequences. We divide motion sequences to short-term movements, and then characterize them based on the distribution of those movements. Motion signatures allow segmenting, retrieving, and synthesizing contextually similar motions.

DOI paper video database bibtex project page

Style-based Motion Analysis for Dance Composition

Andreas Aristidou, Efstathios Stavrakis, Margarita Papaefthimiou, George Papagiannakis, Yiorgos Chrysanthou

The Visual Computer, 34(12), 1725-1737, Dec 2018

This work presents a motion analysis and synthesis framework, based on Laban Movement Analysis, that respects stylistic variations and thus is suitable for dance motion synthesis. Implemented in the context of Motion Graphs, it is used to eliminate potentially problematic transitions and synthesize style-coherent animation, without requiring prior labeling of the data.

DOI paper video database bibtex project page

How Responsiveness, Group Membership and Gender Affect the Feeling of Presence in Immersive Virtual Environments Populated With Virtual Crowds

Marios Kyriakou and Yiorgos Chrysanthou

Presented at: ACM SIGGRAPH Conference on Motion, Interaction, and Games, MIG'18, Limassol, Cyprus, Nov 2018


Inverse Kinematics Techniques in Computer Graphics: A Survey

Andreas Aristidou, Joan Lasenby, Yiorgos Chrysanthou, Ariel Shamir

Computer Graphics Forum, 37(6): 35-58, Sep 2018

Presented at: Eurographics 2018 (STAR paper).

In this survey, we present a comprehensive review of the IK problem and the solutions developed over the years from the computer graphics point of view. The most popular IK methods are discussed with regard to their performance, computational cost and the smoothness of their resulting postures, while we suggest which IK family of solvers is best suited for particular problems. Finally, we indicate the limitations of the current IK methodologies and propose future research directions.

DOI paper bibtex project page

Self-similarity Analysis for Motion Capture Cleaning

Andreas Aristidou, Daniel Cohen-Or, Jessica K. Hodgins, Ariel Shamir

Computer Graphics Forum, 37(2): 297-309, May 2018

Presented at: Eurographics 2018

Our method automatically analyzes mocap sequences of closely interacting performers based on self-similarity. We define motion-words consisting of short-sequences of joints transformations, and use a time-scale invariant similarity measure that is outlier-tolerant to find the KNN. This allows detecting abnormalities and suggesting corrections.

DOI paper video bibtex project page

Virtual Environment Navigation Assisted by Neural Networks

Georgios Kyrlitsias, Amyr Borges Fortes Neto, Panayiotis Charalambous, Marios Avraamides, Yiorgos Chrysanthou

Presented at: Virtual Humans and Crowds for Immersive Environments (VHCIE '18), May 2018

Applications using Virtual Environments (VE) are becoming increasingly popular due to greater computational capacity and improvements in graphics processing units and tracking devices. As a result, much research has been carried out on various aspects of VEs, including the input devices that can be used to navigate scenes when physical movement is not permitted. Here, we test whether implementing a neural network to assist users avoid collisions with virtual obstacles, can benefit the navigation experience. Our hypothesis was that users with no gaming experience in particular, would appreciate the assistance of the neural network in navigation. However, our pilot data suggest the exact opposite: participants with video game experience liked the assisted navigation more than participants with no video game experience.


Hand Tracking with Physiological Constraints

Andreas Aristidou

The Visual Computer, 34(2): 213-228, Jan 2018

We present a simple and efficient methodology for tracking and reconstructing 3D hand poses. Using an optical motion capture system, where markers are positioned at strategic points, we manage to acquire the movement of the hand and establish its orientation using a minimum number of markers. An Inverse Kinematics solver was then employed to control the postures of the hand, subject to physiological constraints that restrict the allowed movements to a feasible and natural set.

DOI paper video bibtex project page

Interaction with virtual crowd in Immersive and semi‐Immersive Virtual Reality systems

Marios Kyriakou, Xueni Pan, Yiorgos Chrysanthou

Comp. Animation & Virtual Worlds, 28(5): e1729, Sep 2017


Emotion Control of Unstructured Dance Movements

Andreas Aristidou, Qiong Zeng, Efstathios Stavrakis, KangKang Yin, Daniel Cohen-Or, Yiorgos Chrysanthou, Baoquan Chen

Presented at: ACM SIGGRAPH/ Eurographics Symposium on Computer Animation, SCA'17. Eurographics Association, Jul 2017

We present a motion stylization technique suitable for highly expressive mocap data, such as contemporary dances. The method varies the emotion expressed in a motion by modifying its underlying geometric features. Even non-expert users can stylize dance motions by supplying an emotion modification as the single parameter of our algorithm.

DOI paper video code bibtex project page

Improving Tracking Accuracy Using Illumination Neutralization and High-Dynamic Range Imaging

Nikolas Ladas, Yiorgos Chrysanthou, Celine Loscos

High Dynamic Range Video Concepts, Technologies and Applications, ed. by Alan Chalmers, Patrizio Campisi, Peter Shirley, and Igor Olaizola. 1st edition. Academic Press. pp. 203–213, Jun 2017


Probabilistic Background Modelling for Sports Video Segmentation

Nikolas Ladas, Paris Kaimakis, Yiorgos Chrysanthou

Presented at: 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, pp 517-525, Porto, Portugal, Jan 2017


Continuous body emotion recognition system during theater performances

Simon Senecal, Louis Cuel, Andreas Aristidou, Nadia Magnenat-Thalmann

Comp. Animation & Virtual Worlds, 27(3-4): 311-320, May 2016

Presented at: Computer Animation and Social Agents - CASA'16

We propose a system for continuous emotional behavior recognition expressed by people during communication based on their gesture and their whole body dynamical motion. The features used to classify the motion are inspired by the Laban Movement Analysis. Using a trained neural network and annotated data, our system is able to describe the motion behavior as trajectories on the Russell Circumplex Model diagram during theater performances over time.

DOI paper bibtex