05 2023 档案

Realistic talking video generation from image and text using StyleGAN and LipGAN
摘要：https://github.com/NethraGunti/Woven-Artificial-Profile-WARP-Face-Video-Synthesis-from-Profile-and-Audio 阅读全文
posted @ 2023-05-29 19:01 郭新晨 阅读(10) 评论(0) 推荐(0)
The project tries to solve a speaker diarization problem using audio features, face recognition and video feature extraction from face image, mouth tracking.
摘要：https://github.com/valiakon/MultimodalAnalysis_SpeakerDiarization 阅读全文
posted @ 2023-05-29 17:54 郭新晨 阅读(14) 评论(0) 推荐(0)
Code for "Audio-driven Talking Face Video Generation with Learning-based Personalized Head Pose"
摘要：https://github.com/yiranran/Audio-driven-TalkingFace-HeadPose 阅读全文
posted @ 2023-05-29 15:23 郭新晨 阅读(13) 评论(0) 推荐(0)