前言
汇总数字人相关技术论文&工具,文章按时间倒序排列,这里没有对方法做细粒度的分类。
Distangled face representation learning & Face Reenactment
会议/时间 | 方法 | 摘要 |
---|---|---|
MM 2022 | MegaPortraits: One-shot Megapixel Neural Head Avatars, paper |
Talking-Face Generation
单位/会议/时间 | 方法 | 摘要 |
---|---|---|
– | Awesome-Talking-Face: https://github.com/JosephPai/Awesome-Talking-Face | 论文列表 |
arxiv, 2024 | VASA-1, VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time, 未开源 | |
2024 | AniPortrait, https://github.com/Zejun-Yang/AniPortrait | |
2024 | MuseTalk, https://github.com/TMElyralab/MuseTalk | |
CVPR 2024 | SyncTalk, https://github.com/ziqiaopeng/SyncTalk | |
CVPR 2023 | Sadtalker: https://github.com/OpenTalker/SadTalker | |
CVPR 2023 | DPE: Disentanglement of Pose and Expression for General Video Portrait Editing | |
CVPR 2023 | StyleSync: High-Fidelity Generalized and Personalized Lip Sync in Style-based Generator | |
ICCV 2023 | ER-NeRF: https://github.com/Fictionarry/ER-NeRF/tree/main | |
under review | GeneFace++: https://genefaceplusplus.github.io/ | |
ICLR 2023 | Geneface: https://github.com/yerfor/GeneFace | |
SIGGRAPH-A 2022 | VideoRetalking: https://github.com/OpenTalker/video-retalking | |
ICCV 2021 | PIRender: https://github.com/RenYurui/PIRender | |
ICCV 2021 | AD-NeRF: https://github.com/YudongGuo/AD-NeRF | |
ACMM 2020 | Wave2Lip: https://github.com/Rudrabha/Wav2Lip | |
ICASSP 2022 | Text2Video: text-driven talking-head video synthesis with phonetic dictionary, [paper] [code] | – |
– | https://github.com/DinoMan/speech-driven-animation | – |
一些常用的专有名词
英文 | 中文 |
---|---|
head pose | |
facial expresion |