Globally and locally consistent image completion

鉴别器 图像(数学) 人工智能 一致性(知识库) 计算机科学 背景(考古学) 卷积神经网络 对比度(视觉) 计算机视觉 模式识别(心理学) 地理 电信 探测器 考古
作者
Satoshi Iizuka,Edgar Simo‐Serra,Hiroshi Ishikawa
出处
期刊:ACM Transactions on Graphics [Association for Computing Machinery]
卷期号:36 (4): 1-14 被引量:2094
标识
DOI:10.1145/3072959.3073659
摘要

We present a novel approach for image completion that results in images that are both locally and globally consistent. With a fully-convolutional neural network, we can complete images of arbitrary resolutions by filling-in missing regions of any shape. To train this image completion network to be consistent, we use global and local context discriminators that are trained to distinguish real images from completed ones. The global discriminator looks at the entire image to assess if it is coherent as a whole, while the local discriminator looks only at a small area centered at the completed region to ensure the local consistency of the generated patches. The image completion network is then trained to fool the both context discriminator networks, which requires it to generate images that are indistinguishable from real ones with regard to overall consistency as well as in details. We show that our approach can be used to complete a wide variety of scenes. Furthermore, in contrast with the patch-based approaches such as PatchMatch, our approach can generate fragments that do not appear elsewhere in the image, which allows us to naturally complete the images of objects with familiar and highly specific structures, such as faces.

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
大幅提高文件上传限制,最高150M (2024-4-1)

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
老鹰发布了新的文献求助20
1秒前
2秒前
MY完成签到,获得积分10
2秒前
大模型应助单纯的寄云采纳,获得10
3秒前
4秒前
给阿硕的情书完成签到 ,获得积分10
4秒前
4秒前
木子李完成签到,获得积分10
4秒前
0128lun应助弯弯采纳,获得150
4秒前
xg发布了新的文献求助10
5秒前
此身越重洋完成签到,获得积分10
6秒前
默默的走发布了新的文献求助10
7秒前
7秒前
所所应助方圆几里采纳,获得10
7秒前
shawn发布了新的文献求助10
7秒前
研友_VZG7GZ应助调皮汽车采纳,获得10
8秒前
广州城建职业技术学院完成签到,获得积分10
9秒前
北风语完成签到,获得积分10
9秒前
彭于晏应助science HY采纳,获得10
9秒前
9秒前
跳跃的访烟完成签到 ,获得积分10
11秒前
英俊的铭应助乔心采纳,获得10
11秒前
写不出来完成签到,获得积分10
11秒前
果子发布了新的文献求助10
13秒前
伊可完成签到 ,获得积分10
16秒前
Q123ba叭发布了新的文献求助10
16秒前
zz完成签到,获得积分10
17秒前
龙楼完成签到 ,获得积分10
18秒前
19秒前
19秒前
Why完成签到,获得积分10
20秒前
yuyu完成签到,获得积分10
20秒前
图图没有了大耳朵完成签到,获得积分10
21秒前
22秒前
吴旭东发布了新的文献求助10
22秒前
SciGPT应助龙卷风采纳,获得10
23秒前
羊咩咩哒完成签到,获得积分10
23秒前
24秒前
Mila发布了新的文献求助20
24秒前
24秒前
高分求助中
歯科矯正学 第7版(或第5版) 1004
SIS-ISO/IEC TS 27100:2024 Information technology — Cybersecurity — Overview and concepts (ISO/IEC TS 27100:2020, IDT)(Swedish Standard) 1000
Smart but Scattered: The Revolutionary Executive Skills Approach to Helping Kids Reach Their Potential (第二版) 1000
Semiconductor Process Reliability in Practice 720
GROUP-THEORY AND POLARIZATION ALGEBRA 500
Mesopotamian divination texts : conversing with the gods : sources from the first millennium BCE 500
Days of Transition. The Parsi Death Rituals(2011) 500
热门求助领域 (近24小时)
化学 医学 生物 材料科学 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 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3231168
求助须知:如何正确求助?哪些是违规求助? 2878307
关于积分的说明 8205681
捐赠科研通 2545770
什么是DOI,文献DOI怎么找? 1375365
科研通“疑难数据库(出版商)”最低求助积分说明 647390
邀请新用户注册赠送积分活动 622448