← ArchivePaper2017
Easy Generation of Facial Animation Using Motion Graphs
J. Serra, Ozan Cetinaslan, Shridhar Ravikumar, Veronica Orvalho, Darren Cosker
Builds a motion graph over facial animation clips, so new performances come from walking the graph instead of authoring every expression by hand.
Abstract
Facial animation is a time‐consuming and cumbersome task that requires years of experience and/or a complex and expensive set‐up. This becomes an issue, especially when animating the multitude of secondary characters required, e.g. in films or video‐games. We address this problem with a novel technique that relies on motion graphs to represent a landmarked database. Separate graphs are created for different facial regions, allowing a reduced memory footprint compared to the original data. The common poses are identified using a Euclidean‐based similarity metric and merged into the same node. This process traditionally requires a manually chosen threshold, however, we simplify it by optimizing for the desired graph compression. Motion synthesis occurs by traversing the graph using Dijkstra's algorithm, and coherent noise is introduced by swapping some path nodes with their neighbours. Expression labels, extracted from the database, provide the control mechanism for animation. We present a way of creating facial animation with reduced input that automatically controls timing and pose detail. Our technique easily fits within video‐game and crowd animation contexts, allowing the characters to be more expressive with less effort. Furthermore, it provides a starting point for content creators aiming to bring more life into their characters.
How to read this
- Category
- Journal paper on facial animation synthesis by graph traversal, a Porto and Bath collaboration.
- Contributions
- A motion graph built over facial animation clips, adapting a technique long used for body motion to the face.
- Generation of new facial performances by walking the graph rather than authoring each expression.
- A pipeline aimed at cutting the years of experience or the expensive capture setup that facial animation normally demands.
- Context
- Comes out of the same Porto group as the rest of this cluster and builds on orvalho-rig-transfer-2008 for the underlying rig, with Darren Cosker's Bath group bringing the capture and analysis side. It is the one paper in the cluster that is about generating motion rather than about interfaces for posing.Builds on: Transferring the Rig and Animations from a Character to Different Face Models
- Correctness
- Motion graphs are only as good as the database behind them, and that is the claim to press: a face has far more subtle continuity requirements than a body, and transitions that are numerically smooth can still read as wrong. Check what the transition cost function actually measures and how large the source clip library is. Quality outside the span of the recorded material is not something a graph can invent.
- Clarity
- A proper Computer Graphics Forum paper, well structured, with the graph construction and the transition metric clearly separated. Readable if you have seen body motion graphs before.
- How to read it
- First pass: abstract, the system diagram, the result videos if you can find them, since this is motion and stills undersell it. Second pass: graph construction and transition cost, the two places quality is decided. Third pass: the evaluation, with the size of the clip database in mind.
Built upon by
Nothing yet.
Related work
Keywords
This page summarises the entry and links to its original source. The archive never hosts or redistributes the publication itself.Show it in the full archive list →