| CARVIEW |
Select Language
HTTP/2 301
server: GitHub.com
content-type: text/html
location: https://feiiyin.github.io/StyleHEAT/
access-control-allow-origin: *
strict-transport-security: max-age=31556952
expires: Mon, 29 Dec 2025 15:24:05 GMT
cache-control: max-age=600
x-proxy-cache: MISS
x-github-request-id: C1C7:3ABDEF:8EC58F:A0527E:69529ABC
accept-ranges: bytes
age: 0
date: Mon, 29 Dec 2025 15:14:05 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210034-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1767021245.085075,VS0,VE220
vary: Accept-Encoding
x-fastly-request-id: f7e6eb4441d80ecf74247f5863530c9e9bd74b7e
content-length: 162
HTTP/2 200
server: GitHub.com
content-type: text/html; charset=utf-8
last-modified: Fri, 08 Aug 2025 20:24:07 GMT
access-control-allow-origin: *
strict-transport-security: max-age=31556952
etag: W/"68965ce7-5970"
expires: Mon, 29 Dec 2025 15:24:05 GMT
cache-control: max-age=600
content-encoding: gzip
x-proxy-cache: MISS
x-github-request-id: AB5A:2680BD:8F60EA:A0EBD6:69529ABB
accept-ranges: bytes
age: 0
date: Mon, 29 Dec 2025 15:14:05 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210034-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1767021245.334627,VS0,VE212
vary: Accept-Encoding
x-fastly-request-id: 29885d706916041d41a5cfe2db32bbcffe331375
content-length: 4202
StyleHEAT
StyleHEAT: One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGAN
- Fei Yin 1
- Yong Zhang 2
- Xiaodong Cun 2
- Mingdeng Cao 1
- Yanbo Fan 2
- Xuan Wang 2
- Qingyan Bai 1
- Baoyuan Wu 3
- Jue Wang 2
- Yujiu Yang 1
- 1 Tsinghua University
- 2 Tencent AI Lab
- 3 The Chinese University of Hong Kong
Abstract
We investigate the latent feature space of a pre-trained StyleGAN and discover some excellent spatial transformation properties. Based on the observation, we propose a novel unified framework based on a pre-trained StyleGAN that enables a set of powerful functionalities, i.e., high-resolution video generation, disentangled control by driving video or audio, and flexible face editing.
Links
Videos
Video 1:
Same-identity Reconstruction
Video 2:
Cross-identity Reenactment
Video 3:
Audio Driven
Video 4:
Intuitive Editing
Video 5:
Attribute Editing
Citation
@article{2203.04036,
author = {Yin, Fei and Zhang, Yong and Cun, Xiaodong and Cao, Mingdeng and Fan, Yanbo and Wang, Xuan and Bai, Qingyan and Wu, Baoyuan and Wang, Jue and Yang, Yujiu},
title = {StyleHEAT: One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGAN},
journal = {arxiv:2203.04036},
year = {2022}
}