Animation Lecture
Réviser ces flashcardsGratuit · répétition espacée · iPhone, Android, Mac et web
Toutes les cartes
1
What was the first 3D human face rendering method, pioneered by Frederic Ira Parke in 1972?
Blend Shapes
2
What type of technique is Blend Shapes?
An interpolation technique (blending between target expression meshes).
3
What is the main drawback of Blend Shapes?
A weakness in expressing subtle variety.
4
Who developed the Facial Action Coding System (FACS)?
Paul Ekman
5
What does FACS anatomically split facial expressions into?
Specific muscle movements called Action Units (AUs).
6
According to FACS, which AUs correspond to 'Happiness'?
AU 6 + AU 12
7
According to FACS, which AUs correspond to 'Sadness'?
AU 1 + AU 4 + AU 15
8
What is a key challenge when animating from speech, related to the influence of nearby sounds?
Coarticulation
9
What two inputs does the JALI (Jaw and Lips) model use?
Audio and a text transcript.
10
What algorithm does JALI use for "forced alignment" (syncing phonemes to audio)?
HMM (Hidden Markov Model)
11
What NVIDIA model generates 3D facial animation in real-time from only an audio stream?
Audio2Face (A2F)
12
What deep learning architecture does Audio2Face (A2F) use?
A wav2vec2.0 architecture.
13
What is a key limitation of Audio2Face (A2F)?
It can be inaccurate with background noise and cannot generate natural 'idle' or listening motions.
14
What is the VOCA model good at capturing?
Synthesizing different 3D speaking styles from audio.
15
What model architecture does FaceFormer use for speech-driven animation?
Transformers
16
What specific challenge does the "Learning to Listen" model address?
Animating the non-deterministic facial reactions of a listener in a conversation.
17
What novel rendering technique does the audio-driven UniGAHA model use?
Gaussian Splatting
18
What is the ProbTalk3D model (from Utrecht University) good at generating?
Non-deterministic and emotion-controllable 3D facial animation.
19
What does 3DMM stand for?
3D Morphable Models
20
What are 3DMMs (like FLAME) good at disentangling?
The core components of a face (e.g., shape, expression, pose).
21
What is the RingNet model good at?
Regressing a 3D face shape and expression from a single 2D image.
22
What is the DECA model good at learning from?
"In-the-wild" (uncontrolled) images.
23
What does the SAMPL-X model capture from a single image?
The full expressive body (3D hands, face, and body).
24
What was the massive facial animation challenge for the game Cyberpunk 2077?
Localizing facial animation for 10 different voice-over languages.
25
What model did Cyberpunk 2077 use to solve its animation localization problem?
JALI
26
What did Utrecht University's 'Realism' study find?
Higher appearance and animation realism led to higher perceived social presence and attractiveness.
27
What 'uncanny valley' effect did the 'Familiarity' study on 'digital doubles' find?
Participants could identify their own digital doubles but consistently disliked them, especially realistic versions.
28
In the 'Familiarity' study, who were people more forgiving of?
The digital doubles of acquaintances or unknown persons.
Plus de flashcards : Histoire et lettres
Aerodynamics & AircraftHistoire et lettres · AnglaisPilotRLPoetry Terms and Sonnets Study GuideHistoire et lettres · AnglaisBrothersfanArt Appreciation: Chapters 1 and 2Histoire et lettres · AnglaisColeRK1 history karUHistoire et lettres · RusseАбайUnit 2 Medieval History Study GuideHistoire et lettres · AnglaisBrothersfanKompan 2Histoire et lettres · IndonésienHestiaEOY EXAMHistoire et lettres · AnglaisTNorth America Countries (alphabetically)Histoire et lettres · EspagnolxAP Lesson 3Histoire et lettres · AnglaisYeszalaHistoryHistoire et lettresLeannLong Road Home - CaseyHistoire et lettres · AnglaisLaurmcbrCompare the Mariner and Nora QuotesHistoire et lettres · AnglaisIssy
Tous les decks : Histoire et lettres
Révise ces decks dans l’app
Gratuit sur iPhone, Android, Mac et le web. Ajoute n’importe quel deck à ton compte en un tap.
