Sketch2Photo: Synthesizing photo-realistic images from sketches via global contexts

计算机科学 素描 人工智能 联营 特征(语言学) 地点 卷积(计算机科学) 模式识别(心理学) 算法 人工神经网络 语言学 哲学
作者
Heng Liu,Xu Yao,Feng Chen
出处
期刊:Engineering Applications of Artificial Intelligence [Elsevier BV]
卷期号:117: 105608-105608 被引量:22
标识
DOI:10.1016/j.engappai.2022.105608
摘要

Sketch-to-image synthesis aims to generate realistic images that match the input sketches or edge maps exactly. Most known sketch-to-image synthesis methods use various generative adversarial networks (GANs) that are trained with numerous pairs of sketches and real images. Because of the convolution locality, the low-level layers of the generators in these GANs lack global perception ability, causing feature maps derived from them easily to overlook global cues. Since the global receptive field is crucial for acquiring the non-local structures and features of sketches, the absence of global contexts will impact the generation of high-quality images. Some recent models turn to self-attention to construct global dependencies. However, they are not viable for large feature maps for the quadratic computational complexity concerning the size of feature maps. To address these problems, in this work, we propose Sketch2Photo — a new image synthesis approach that can capture global contexts as well as local features to generate photo-realistic images from weak or partial sketches or edge maps. We employ fast Fourier convolution (FFC) residual blocks to create global receptive fields in the bottom layers of the network and incorporate Swin Transformer block (STB) units to obtain long-range global contexts for large-size feature maps efficiently. We also present an improved spatial attention pooling (ISAP) module to relax the strict alignment requirements between incomplete sketches and generated images. Quantitative and qualitative experiments on multiple public datasets demonstrate the superiority of the proposed approach over many other sketch-to-image synthesis methods. The project code is available at https://github.com/hengliusky/Skecth2Photo.
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
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

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
yikeshu完成签到,获得积分10
刚刚
Zoe完成签到 ,获得积分10
1秒前
3秒前
星辰大海应助do0采纳,获得10
4秒前
tt完成签到 ,获得积分10
5秒前
浅辰完成签到,获得积分10
6秒前
大气萤完成签到,获得积分20
7秒前
7秒前
我ppp完成签到 ,获得积分10
7秒前
8秒前
易燃物品完成签到,获得积分10
8秒前
Hello应助Ther采纳,获得10
10秒前
CherylZhao完成签到,获得积分10
11秒前
Galato发布了新的文献求助10
12秒前
颜愫完成签到,获得积分10
12秒前
安详向日葵完成签到 ,获得积分10
13秒前
拼搏的白云完成签到,获得积分10
13秒前
852应助hhh采纳,获得10
13秒前
李白白白完成签到,获得积分10
13秒前
王手完成签到,获得积分10
13秒前
14秒前
一人完成签到,获得积分10
15秒前
do0完成签到,获得积分10
16秒前
yar应助xlz110采纳,获得10
16秒前
NexusExplorer应助落寞凌波采纳,获得10
18秒前
量子星尘发布了新的文献求助10
21秒前
123完成签到 ,获得积分10
21秒前
哈哈呵完成签到,获得积分10
21秒前
21秒前
Rylee完成签到,获得积分10
21秒前
Jiro完成签到,获得积分10
23秒前
我ppp发布了新的文献求助60
24秒前
25秒前
纳米酶催化完成签到,获得积分10
26秒前
26秒前
John完成签到,获得积分10
26秒前
李小强完成签到,获得积分10
27秒前
28秒前
31秒前
落寞凌波发布了新的文献求助10
31秒前
高分求助中
【提示信息,请勿应助】关于scihub 10000
Les Mantodea de Guyane: Insecta, Polyneoptera [The Mantids of French Guiana] 3000
徐淮辽南地区新元古代叠层石及生物地层 3000
The Mother of All Tableaux: Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 3000
Handbook of Industrial Diamonds.Vol2 1100
Global Eyelash Assessment scale (GEA) 1000
Picture Books with Same-sex Parented Families: Unintentional Censorship 550
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 4038368
求助须知:如何正确求助?哪些是违规求助? 3576068
关于积分的说明 11374313
捐赠科研通 3305780
什么是DOI,文献DOI怎么找? 1819322
邀请新用户注册赠送积分活动 892672
科研通“疑难数据库(出版商)”最低求助积分说明 815029