https://github.com/Weijian-li/unsupervised_inter_intra_landmark
Structured Landmark Detection via Topology-Adapting Deep Graph Learning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Facial tasks in machine learning operate based on images or video frames (or other datasets) focussed on human faces.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Structured Landmark Detection via Topology-Adapting Deep Graph Learning
Facial Motion Prior Networks for Facial Expression Recognition
Facial Motion Prior Networks for Facial Expression Recognition
Progressive Growing of GANs for Improved Quality, Stability, and Variation
Progressive Growing of GANs for Improved Quality, Stability, and Variation
3D Face Reconstruction from A Single Image Assisted by 2D Face Images in the Wild
3D Face Reconstruction from A Single Image Assisted by 2D Face Images in the Wild
Very Deep Convolutional Networks for Large-Scale Image Recognition
DeepFaceLab: Integrated, flexible and extensible face-swapping framework
Circle Loss: A Unified Perspective of Pair Similarity Optimization
ArcFace: Additive Angular Margin Loss for Deep Face Recognition
ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
Very Deep Convolutional Networks for Large-Scale Image Recognition
Live Speech Portraits: Real-Time Photorealistic Talking-Head Animation
Unsupervised Discovery of Object Landmarks as Structural Representations
ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
RetinaFace: Single-stage Dense Face Localisation in the Wild
Very Deep Convolutional Networks for Large-Scale Image Recognition
Few-Shot Adversarial Learning of Realistic Neural Talking Head Models
Few-Shot Adversarial Learning of Realistic Neural Talking Head Models
Very Deep Convolutional Networks for Large-Scale Image Recognition
Very Deep Convolutional Networks for Large-Scale Image Recognition
Very Deep Convolutional Networks for Large-Scale Image Recognition
ArcFace: Additive Angular Margin Loss for Deep Face Recognition
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.