CASIA OpenIR  > 智能感知与计算研究中心
AnyFace++: A Unified Framework for Free-style Text-to-Face Synthesis and Manipulation
Sun, Jianxin; Deng, Qiyao; Li, Qi; Sun, Muyi; Liu, Yunfan; Sun, Zhenan
Source PublicationIEEE Transactions on Pattern Analysis and Machine Intelligence
2024
Pages1-15
Abstract

Human faces contain rich semantic information that could hardly be described without a large vocabulary and complex sentence patterns. However, most existing text-to-image synthesis methods could only generate meaningful results based on limited sentence templates with words contained in the training set, which heavily impairs the generalization ability of these models. In this paper, we define a novel ‘free-style’ text-to-face generation and manipulation problem, and propose an effective solution, named AnyFace++, which is applicable to a much wider range of open-world scenarios. The CLIP model is involved in AnyFace++ for learning an aligned language-vision feature space, which also expands the range of acceptable vocabulary as it is trained on a large-scale dataset. To further improve the granularity of semantic alignment between text and images, a memory module is incorporated to convert the description with arbitrary length, format, and modality into regularized latent embeddings representing discriminative attributes of the target face. Moreover, the diversity and semantic consistency of generation results are improved by a novel semi-supervised training scheme and a series of newly proposed objective functions. Compared to state-of-the-art methods, AnyFace++ is capable of synthesizing and manipulating face images based on more flexible descriptions and producing realistic images with higher diversity.

Language英语
IS Representative Paper
Sub direction classification生物特征识别
planning direction of the national heavy laboratory视觉信息处理
Paper associated data
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/55253
Collection智能感知与计算研究中心
多模态人工智能系统全国重点实验室
Corresponding AuthorLi, Qi
AffiliationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Sun, Jianxin,Deng, Qiyao,Li, Qi,et al. AnyFace++: A Unified Framework for Free-style Text-to-Face Synthesis and Manipulation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2024:1-15.
APA Sun, Jianxin,Deng, Qiyao,Li, Qi,Sun, Muyi,Liu, Yunfan,&Sun, Zhenan.(2024).AnyFace++: A Unified Framework for Free-style Text-to-Face Synthesis and Manipulation.IEEE Transactions on Pattern Analysis and Machine Intelligence,1-15.
MLA Sun, Jianxin,et al."AnyFace++: A Unified Framework for Free-style Text-to-Face Synthesis and Manipulation".IEEE Transactions on Pattern Analysis and Machine Intelligence (2024):1-15.
Files in This Item: Download All
File Name/Size DocType Version Access License
AnyFace_A_Unified_Fr(16839KB)期刊论文出版稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Sun, Jianxin]'s Articles
[Deng, Qiyao]'s Articles
[Li, Qi]'s Articles
Baidu academic
Similar articles in Baidu academic
[Sun, Jianxin]'s Articles
[Deng, Qiyao]'s Articles
[Li, Qi]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Sun, Jianxin]'s Articles
[Deng, Qiyao]'s Articles
[Li, Qi]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: AnyFace_A_Unified_Framework_for_Free-style_Text-to-Face_Synthesis_and_Manipulation.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.