https://github.com/KathyReid/opensource-voice-tools
Flowtron: an Autoregressive Flow-based Generative Network for Text-to-Speech Synthesis
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
What is Human Pose Estimation? Human pose estimation is the process of estimating the configuration of the body (pose) from a single, typically monocular, image. Background. Human pose estimation is one of the key problems in computer vision that has been studied for well over 15 years. The reason for its importance is the abundance of applications that can benefit from such a technology. For example, human pose estimation allows for higher-level reasoning in the context of human-computer interaction and activity recognition; it is also one of the basic building blocks for marker-less motion capture (MoCap) technology. MoCap technology is useful for applications ranging from character animation to clinical analysis of gait pathologies.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Flowtron: an Autoregressive Flow-based Generative Network for Text-to-Speech Synthesis
Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis
Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
Seen and Unseen emotional style transfer for voice conversion with a new emotional speech dataset
StyleGaussian: Instant 3D Style Transfer with Gaussian Splatting
Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings
Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis
XGAN: Unsupervised Image-to-Image Translation for Many-to-Many Mappings
DCT-Net: Domain-Calibrated Translation for Portrait Stylization
Unsupervised Meta-learning of Figure-Ground Segmentation via Imitating Visual Effects
HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation
Accurate Image Super-Resolution Using Very Deep Convolutional Networks
ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
Accurate Image Super-Resolution Using Very Deep Convolutional Networks
Stroke Controllable Fast Style Transfer with Adaptive Receptive Fields
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.