Self-Supervised Learning for Real-World Super-Resolution from Dual and Multiple Zoomed Observations

人工智能 计算机科学 计算机视觉 基本事实 图像(数学) 特征(语言学) 图像分辨率 超分辨率 对偶(语法数字) 模式识别(心理学) 艺术 文学类 哲学 语言学
作者
Zhilu Zhang,Ruohao Wang,Hongzhi Zhang,Wangmeng Zuo
出处
期刊:IEEE Transactions on Pattern Analysis and Machine Intelligence [IEEE Computer Society]
卷期号:: 1-13 被引量:1
标识
DOI:10.1109/tpami.2024.3379736
摘要

In this paper, we consider two challenging issues in reference-based super-resolution (RefSR) for smartphone, (i) how to choose a proper reference image, and (ii) how to learn RefSR in a self-supervised manner. Particularly, we propose a novel self-supervised learning approach for real-world RefSR from observations at dual and multiple camera zooms. Firstly, considering the popularity of multiple cameras in modern smartphones, the more zoomed (telephoto) image can be naturally leveraged as the reference to guide the super-resolution (SR) of the lesser zoomed (ultra-wide) image, which gives us a chance to learn a deep network that performs SR from the dual zoomed observations (DZSR). Secondly, for self-supervised learning of DZSR, we take the telephoto image instead of an additional high-resolution image as the supervision information, and select a center patch from it as the reference to super-resolve the corresponding ultra-wide image patch. To mitigate the effect of the misalignment between ultra-wide low-resolution (LR) patch and telephoto ground-truth (GT) image during training, we first adopt patch-based optical flow alignment to obtain the warped LR, then further design an auxiliary-LR to guide the deforming of the warped LR features. To generate visually pleasing results, we present local overlapped sliced Wasserstein loss to better represent the perceptual difference between GT and output in the feature space. During testing, DZSR can be directly deployed to super-solve the whole ultra-wide image with the reference of the telephoto image. In addition, we further take multiple zoomed observations to explore self-supervised RefSR, and present a progressive fusion scheme for the effective utilization of reference images. Experiments show that our methods achieve better quantitative and qualitative performance against state-of-the-arts. The code and pre-trained models will be publicly available.
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
sheila发布了新的文献求助10
刚刚
fyneru完成签到,获得积分10
1秒前
鲤鱼依珊发布了新的文献求助10
1秒前
1秒前
2秒前
酷酷怜雪发布了新的文献求助10
2秒前
桓某人发布了新的文献求助10
2秒前
紹魟完成签到 ,获得积分10
3秒前
稳重的馒头完成签到,获得积分10
4秒前
LHH完成签到,获得积分10
4秒前
5秒前
JamesPei的应助被楠1111采纳,获得10
5秒前
Nov2完成签到,获得积分20
5秒前
5秒前
5秒前
6秒前
7秒前
Popo发布了新的文献求助10
7秒前
gqz发布了新的文献求助10
8秒前
8秒前
留胡子的小甜瓜完成签到,获得积分10
10秒前
饼的书发布了新的文献求助10
10秒前
10秒前
kokoro发布了新的文献求助10
11秒前
zehua309完成签到,获得积分10
11秒前
大菠萝完成签到,获得积分20
13秒前
ANmin完成签到 ,获得积分10
15秒前
十年完成签到 ,获得积分20
15秒前
peng发布了新的文献求助10
15秒前
赘婿的应助被gqz采纳,获得10
16秒前
16秒前
kokoro完成签到,获得积分20
17秒前
旋指动青天完成签到,获得积分10
17秒前
17秒前
fantasy的应助被Sue采纳,获得10
19秒前
19秒前
Christine完成签到,获得积分10
19秒前
爆米花的应助被weiwei采纳,获得10
21秒前
美丽蕨菜子完成签到,获得积分10
21秒前
Akim的应助被飞辉灰采纳,获得10
21秒前
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 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
八旗制度の研究 600
Improving the wear resistance of vehicle gear oil by oil soluble LaF3 nanoparticles and typical additives of gear oil 500
Boundaries and Bodhisattvas 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 8183403
求助须知:如何正确求助?哪些是违规求助? 9572654
关于积分的说明 21826992
捐赠科研通 7780463
什么是DOI,文献DOI怎么找? 3434008
关于科研通互助平台的介绍 2558183
邀请新用户注册赠送积分活动 2480337