https://github.com/shuliyao/GANimation_TL
GANimation: Anatomically-aware Facial Animation from a Single Image
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.
GANimation: Anatomically-aware Facial Animation from a Single Image
Deep High-Resolution Representation Learning for Visual Recognition
ArcFace: Additive Angular Margin Loss for Deep Face Recognition
Progressive Growing of GANs for Improved Quality, Stability, and Variation
Progressive Growing of GANs for Improved Quality, Stability, and Variation
Progressive Growing of GANs for Improved Quality, Stability, and Variation
Efficient Facial Feature Learning with Wide Ensemble-based Convolutional Neural Networks
RetinaFace: Single-stage Dense Face Localisation in the Wild
Deep High-Resolution Representation Learning for Visual Recognition
ArcFace: Additive Angular Margin Loss for Deep Face Recognition
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
ArcFace: Additive Angular Margin Loss for Deep Face Recognition
Progressive Growing of GANs for Improved Quality, Stability, and Variation
BlendGAN: Implicitly GAN Blending for Arbitrary Stylized Face Generation
Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervision
Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervision
FaceNet: A Unified Embedding for Face Recognition and Clustering
Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.