Playable universal capture

Borshukov, George; Montgomery, Jefferson; Werner, Witek

doi:10.1145/1185657.1185848

Cited by 4 publications

(2 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We use contact information within a physical simulation to drive the color changes. This is similar to playable universal capture [Borshukov et al 2007], except that the texture appearance is driven by simulated attributes (contacts in the physics simulation) rather than a previously recorded appearance trajectory.…”

Section: Related Workmentioning

confidence: 95%

Data-driven Fingertip Appearance for Interactive Hand Simulation

Andrews

Jarvis

Kry

2013

Proceedings of Motion on Games

View full text Add to dashboard Cite

Contact on a finger pad results in deformation that redistributes blood within the fingertip tissue in a manner correlated to the pressure. We build a data-driven model that relates contact information to the visible changes of the finger nail and surrounding tissue on the back of the finger tip. Our data analysis and model construction makes use of the space of hemoglobin concentrations, as opposed to an RGB color space, which permits the model to be transferred across different fingers and different people. We use principal component analysis to build a compact model which maps well to graphics hardware with an efficient fragment program implementation. We provide a validation of our model, and a demonstration of a grasping controller running in a physically based simulation, where grip strength is visible in both hand posture and the appearance of color changes at the fingertips.

show abstract

Section: Related Workmentioning

confidence: 95%

Data-driven Fingertip Appearance for Interactive Hand Simulation

Andrews

Jarvis

Kry

2013

Proceedings of Motion on Games

View full text Add to dashboard Cite

show abstract

“…To circumvent these limitations, several image-based approaches like [8][9][10][11][12][13][14][15][16][17] have been developed. For example in [13], a low-cost system for facial performance transfer is presented.…”

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