Prestasi Wajah: 3 Petua Penting untuk Protokol Pengambilan Data

Apabila anda mereka bentuk protokol tangkapan wajah, terdapat begitu banyak perkara yang perlu anda pertimbangkan untuk mengelakkan hasil data berkualiti rendah dan keletihan peserta.

Faktor-faktor seperti…

pose apa yang anda pilih
bagaimana anda menyusun urutan pose
bagaimana anda menerangkan/menunjukkan pose-pose tersebut, dan sebagainya.

…membuat perbezaan besar dalam hasil sesi anda.

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.

Terdapat senarai tanpa henti tentang perkara yang boleh dan tidak boleh dilakukan untuk reka bentuk tangkapan wajah, tetapi berikut adalah beberapa petua umum:

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 dan 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!

📝 Satu lagi petuaDalam video itu, perhatikan bagaimana saya mengarahkan aksi yang dikenali sebagai chin raiser dengan berkata “dorong bibir bawah anda ke atas.” Mudah untuk terperangkap dalam menerangkan pose berdasarkan nama rasmi mereka, tetapi dengan menggunakan deskriptor yang lebih mudah difahami, anda boleh meningkatkan kebarangkalian peserta anda mencapai pose tersebut.