https://github.com/Francis-Rings/StableAnimator
공식 코드StableAnimator: High-Quality Identity-Preserving Human Image Animation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Face Reenactment is an emerging conditional face synthesis task that aims at fulfilling two goals simultaneously: 1) transfer a source face shape to a target face; while 2) preserve the appearance and the identity of the target face.
Source: One-shot Face Reenactment
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
StableAnimator: High-Quality Identity-Preserving Human Image Animation
LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control
SMILE: Semantically-guided Multi-attribute Image and Layout Editing
BakedAvatar: Baking Neural Fields for Real-Time Head Avatar Synthesis
3DFaceShop: Explicitly Controllable 3D-Aware Portrait Generation
AnimeCeleb: Large-Scale Animation CelebHeads Dataset for Head Reenactment
StyleAvatar: Real-time Photo-realistic Portrait Avatar from a Single Video
AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation
HyperReenact: One-Shot Reenactment via Jointly Learning to Refine and Retarget Faces
Finding Directions in GAN's Latent Space for Neural Face Reenactment
StyleMask: Disentangling the Style Space of StyleGAN2 for Neural Face Reenactment
MagicPortrait: Temporally Consistent Face Reenactment with 3D Geometric Guidance
ReliableSwap: Boosting General Face Swapping Via Reliable Supervision
ICface: Interpretable and Controllable Face Reenactment Using GANs
APB2Face: Audio-guided face reenactment with auxiliary pose and blink signals
AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation
APB2Face: Audio-guided face reenactment with auxiliary pose and blink signals
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.