https://github.com/xuyingzhongguo/deepfakeannotations
공식 코드Analyzing Fairness in Deepfake Detection With Massively Annotated Databases
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
3D Face Reconstruction is a computer vision task that involves creating a 3D model of a human face from a 2D image or a set of images. The goal of 3D face reconstruction is to reconstruct a digital 3D representation of a person's face, which can be used for various applications such as animation, virtual reality, and biometric identification.
<span style="color:grey; opacity: 0.6">( Image credit: 3DDFA_V2 )</span>
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Analyzing Fairness in Deepfake Detection With Massively Annotated Databases
Learning Pairwise Interaction for Generalizable DeepFake Detection
VoD: Learning Volume of Differences for Video-Based Deepfake Detection
EMO-LLaMA: Enhancing Facial Emotion Understanding with Instruction Tuning
Distract Your Attention: Multi-head Cross Attention Network for Facial Expression Recognition
Comprehensive Layer-wise Analysis of SSL Models for Audio Deepfake Detection
Boosting the Adversarial Transferability of Surrogate Models with Dark Knowledge
Real3D-Portrait: One-shot Realistic 3D Talking Portrait Synthesis
Unlocking the Hidden Potential of CLIP in Generalizable Deepfake Detection
ReliableSwap: Boosting General Face Swapping Via Reliable Supervision
RestorerID: Towards Tuning-Free Face Restoration with ID Preservation
Face Recognition via Locality Constrained Low Rank Representation and Dictionary Learning
Face recognition via compact second order image gradient orientations
Self-supervised Re-renderable Facial Albedo Reconstruction from Single Image
Vision Transformer with Attentive Pooling for Robust Facial Expression Recognition
VidFace: A Full-Transformer Solver for Video FaceHallucination with Unaligned Tiny Snapshots
Efficient Emotional Adaptation for Audio-Driven Talking-Head Generation
Multi-scale Promoted Self-adjusting Correlation Learning for Facial Action Unit Detection
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.