Rendimiento facial: 3 consejos esenciales para los protocolos de captura de datos

A la hora de diseñar protocolos de captura facial, hay muchos aspectos que deben tenerse en cuenta para evitar la obtención de datos de baja calidad y el cansancio de los participantes.

Factores como...

qué poses elegir
cómo se secuencian las posturas
cómo explicas/muestras las poses, etc.

...marcan una gran diferencia en el resultado de tus sesiones.

Working with major game and tech companies to refine their facial performance capture pipelines, it’s quite obvious that people are recycling similar, dated protocols. Considering the present purpose of many captures, such old protocols are often clunky with illogical pose combinations, redundant expressions, and inefficient flow.

Hay una lista interminable de lo que se debe y no se debe hacer en el diseño de capturas faciales, pero he aquí algunos consejos generales:

1. Be use case-minded!

Are you defining machine learning training data for real-time applications? Are you gathering extreme poses for high-intensity fight scenes in film or games? Think about your end goal.

If your purpose is to capture facial data for an avatar product aimed toward co-working, you’d likely want to prioritize prosocial, collaborative, and natural facial expressions. Stop wasting time, energy, and production budget by bloating your session with every possible unsightly “scream” pose or hyper-compressed “lemon” face. Save those for Diablo y Planet of the Apes.

2. Design for logical flow.

Group similar expressions together, e.g. brow-based FACS poses (action units like – inner brow raiser, outer brow raiser, brow lowerer) and eye-based FACS poses (action units like – upper lid raiser, lid tightener, cheek raiser, eye closure, blink, wink) together.
Go from easy to difficult within each section. If you move from easy to difficult across ALL poses, you will end up forcing your user to leap from eyes to mouth to brows to jaw.
Grouping expressions strategically not only helps with user fatigue and comprehension, but it also opens up opportunity to order your poses in a way that allows you to describe and build off previous ones.

3. Make sure your example imagery and descriptions match the target pose and intended blendshapes.

Too many times, I see prompts like “raise brows without widening eyes” – yet the actor in the example shot is clearly widening their eyes. A large percentage of users will do as they see, not as they hear or read. So, don’t give conflicting instructions, and make sure you rigorously review the example poses!

📝 Un consejo más: En el vídeo, fíjate en cómo indico la acción conocida como levantar la barbilla diciendo "empuja hacia arriba el labio inferior". Es fácil atascarse en la descripción de las posturas basándose en sus nombres formales, pero si utilizas descriptores más accesibles puedes aumentar la probabilidad de que tu participante acierte con la postura.