亲爱的研友该休息了!由于当前在线用户较少,发布求助请尽量完整地填写文献信息,科研通机器人24小时在线,伴您度过漫漫科研夜!身体可是革命的本钱,早点休息,好梦!

Interactive Generative Adversarial Networks with High-Frequency Compensation for Facial Attribute Editing

计算机科学 对抗制 生成语法 人工智能 补偿(心理学) 语音识别 图像编辑 图像(数学) 精神分析 心理学
作者
Wenmin Huang,Weiqi Luo,Xiaochun Cao,Jiwu Huang
出处
期刊:IEEE Transactions on Circuits and Systems for Video Technology [Institute of Electrical and Electronics Engineers]
卷期号:34 (9): 8215-8229
标识
DOI:10.1109/tcsvt.2024.3391348
摘要

Recently, facial attribute editing has drawn increasing attention and has achieved significant progress due to Generative Adversarial Network (GAN). Since paired images before and after editing are not available, existing methods typically perform the editing and reconstruction tasks simultaneously, and transfer facial details learned from the reconstruction to the editing via sharing the latent representation space and weights. In this way, they can not preserve those non-targeted regions well during editing. In addition, they usually introduce skip connections between the encoder and decoder to improve image quality at the cost of attribute editing ability. In this paper, we propose a novel method called InterGAN with high-frequency compensation to alleviate above problems. Specifically, we first propose the cross-task interaction (CTI) to fully explore the relationships between editing and reconstruction tasks. The CTI includes two translations: style translation adjusts the mean and variance of feature maps according to style features, and conditional translation utilizes attribute vector as condition to guide feature map transformation. They provide effective information interaction to preserve the irrelevant regions unchanged. Without using skip connections between the encoder and decoder, furthermore, we propose the high-frequency compensation module (HFCM) to improve image quality. The HFCM tries to collect potentially loss information from input images and each down-sampling layers of the encoder, and then re-inject them into subsequent layers to alleviate the information loss. Ablation analysis show the effectiveness of proposed CTI and HFCM. Extensive qualitative and quantitative experiments on CelebA-HQ demonstrate that the proposed method outperforms state-of-the-art methods both in attribute editing accuracy and image quality.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
辛勤尔珍完成签到,获得积分10
3秒前
5秒前
5秒前
7秒前
0212w发布了新的文献求助10
13秒前
xiaoyunfei完成签到,获得积分10
16秒前
woxiangtangping完成签到,获得积分10
30秒前
小绵羊完成签到,获得积分10
30秒前
秃然完成签到,获得积分10
30秒前
找星星的小鱼完成签到 ,获得积分10
40秒前
华山小将完成签到 ,获得积分10
41秒前
苗条的香萱完成签到,获得积分10
41秒前
无花果的应助被年轻的老人采纳,获得10
44秒前
自由的小熊猫完成签到,获得积分10
45秒前
47秒前
48秒前
50秒前
水晶果变萌完成签到 ,获得积分10
53秒前
wow发布了新的文献求助10
54秒前
56秒前
syvshc的应助被chen采纳,获得10
59秒前
lucy完成签到,获得积分20
59秒前
lucy发布了新的文献求助30
1分钟前
仰勒完成签到 ,获得积分10
1分钟前
今后的应助被爱听歌笑寒采纳,获得10
1分钟前
1分钟前
团宝妞宝完成签到,获得积分10
1分钟前
1分钟前
1分钟前
GE完成签到 ,获得积分10
1分钟前
1分钟前
1分钟前
1分钟前
CipherSage的应助被smsk采纳,获得10
1分钟前
yizhiyang发布了新的文献求助10
1分钟前
1分钟前
章鱼烧完成签到 ,获得积分10
1分钟前
1分钟前
1分钟前
别别完成签到,获得积分10
1分钟前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 2000
Handbook of Sport Coaching Research 1000
Orthognathic Surgery - 2 Volume Set 500
高分子基功能界面水蒸发材料与应用研究 500
外场增强的水汽发电研究 500
基于结构调控的功能化水诱导发电材料与器件研究 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8195028
求助须知:如何正确求助?哪些是违规求助? 9580770
关于积分的说明 21872653
捐赠科研通 7794788
什么是DOI,文献DOI怎么找? 3437886
关于科研通互助平台的介绍 2561176
邀请新用户注册赠送积分活动 2484562