Everybody Dance Now

Webber, Sarah; Harrop, Mitchell; Downs, John; Cox, Travis; Wouters, Niels; Moere, Andrew Vande

doi:10.1145/2838739.2838801

Cited by 4 publications

(1 citation statement)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While deep models were initially used to generate realistic images or modify them, GANs are also capable of performing image to image translation tasks, as demonstrated in [26, 27]. In these examples, the output images of GANs are conditioned on source images, which usually represent the ‘content’ and the task of the GAN is generating new images that show the same content (e.g.…”

Section: Related Workmentioning

confidence: 99%

Interactive facial animation with deep neural networks

Paier

Hilsmann

Eisert

2020

IET Computer Vision

View full text Add to dashboard Cite

Creating realistic animations of human faces is still a challenging task in computer graphics. While computer graphics (CG) models capture much variability in a small parameter vector, they usually do not meet the necessary visual quality. This is due to the fact, that geometry‐based animation often does not allow fine‐grained deformations and fails in difficult areas (mouth, eyes) to produce realistic renderings. Image‐based animation techniques avoid these problems by using dynamic textures that capture details and small movements that are not explained by geometry. This comes at the cost of high‐memory requirements and limited flexibility in terms of animation because dynamic texture sequences need to be concatenated seamlessly, which is not always possible and prone to visual artefacts. In this study, the authors present a new hybrid animation framework that exploits recent advances in deep learning to provide an interactive animation engine that can be used via a simple and intuitive visualisation for facial expression editing. The authors describe an automatic pipeline to generate training sequences that consist of dynamic textures plus sequences of consistent three‐dimensional face models. Based on this data, they train a variational autoencoder to learn a low‐dimensional latent space of facial expressions that is used for interactive facial animation.

show abstract

Section: Related Workmentioning

confidence: 99%

Interactive facial animation with deep neural networks

Paier

Hilsmann

Eisert

2020

IET Computer Vision

View full text Add to dashboard Cite

show abstract

SimonXXL - Investigating Spontaneous Group Formation Around Public Installations

Jacobsen

Svendsen

Søgaard

et al. 2020

Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering

View full text Add to dashboard Cite

In this paper, we set out to explore how to design for spontaneous group formation, as part of shared encounters in a public installation. Spontaneous group formation describes a phenomenon where pedestrians form groups with other pedestrians, to whom they are previously unacquainted, for the purpose of interacting with an installation. This was accomplished by developing a 5 by 5 meter version of the game based on the Simon game, with flashing lights and oversized buttons, designed to encourage spontaneous group formation by giving an advantage to larger groups, up to a maximum of four. Over three days of testing, the prototype was found to generate 11 spontaneous group formations out of 161 total use cases, showing evidence that effective lures are one of the key factors behind the phenomenon.

show abstract