3D Face Animation
21 papers with code • 3 benchmarks • 6 datasets
Image: Cudeiro et al
Datasets
PASCAL VOC
VOCASET
BEAT2
Biwi 3D Audiovisual Corpus of Affective Communication - B3D(AC)^2
Human Optical Flow
FEAFA+
Latest papers
LeGO: Leveraging a Surface Deformation Network for Animatable Stylized Face Generation with One Example
To this end, we propose a method that can produce a highly stylized 3D face model with desired topology.
EMAGE: Towards Unified Holistic Co-Speech Gesture Generation via Expressive Masked Audio Gesture Modeling
We propose EMAGE, a framework to generate full-body human gestures from audio and masked gestures, encompassing facial, local body, hands, and global movements.
FaceTalk: Audio-Driven Motion Diffusion for Neural Parametric Head Models
We propose a new latent diffusion model for this task, operating in the expression space of neural parametric head models, to synthesize audio-driven realistic head sequences.
FaceDiffuser: Speech-Driven 3D Facial Animation Synthesis Using Diffusion
uuembodiedsocialai/FaceDiffuser
•
•
In addition, majority of the approaches focus on 3D vertex based datasets and methods that are compatible with existing facial animation pipelines with rigged characters is scarce.
Speech-Driven 3D Face Animation with Composite and Regional Facial Movements
wuhaozhe/audio2face_mm2023
•
•
This paper emphasizes the importance of considering both the composite and regional natures of facial movements in speech-driven 3D face animation.
SelfTalk: A Self-Supervised Commutative Training Diagram to Comprehend 3D Talking Faces
psyai-net/SelfTalk_release
•
•
To enhance the visual accuracy of generated lip movement while reducing the dependence on labeled data, we propose a novel framework SelfTalk, by involving self-supervision in a cross-modals network system to learn 3D talking faces.
Learning Landmarks Motion from Speech for Speaker-Agnostic 3D Talking Heads Generation
fedenoce/s2l-s2d
•
•
This paper presents a novel approach for generating 3D talking heads from raw audio inputs.
EmoTalk: Speech-Driven Emotional Disentanglement for 3D Face Animation
psyai-net/EmoTalk_release
•
•
ICCV 2023
Specifically, we introduce the emotion disentangling encoder (EDE) to disentangle the emotion and content in the speech by cross-reconstructed speech signals with different emotion labels.
MMFace4D: A Large-Scale Multi-Modal 4D Face Dataset for Audio-Driven 3D Face Animation
why986/VFA
•
•
Upon MMFace4D, we construct a non-autoregressive framework for audio-driven 3D face animation.
FaceXHuBERT: Text-less Speech-driven E(X)pressive 3D Facial Animation Synthesis Using Self-Supervised Speech Representation Learning
This paper presents FaceXHuBERT, a text-less speech-driven 3D facial animation generation method that allows to capture personalized and subtle cues in speech (e. g. identity, emotion and hesitation).
