Self-Supervised Learning for RGB-Guided Depth Enhancement by Exploiting the Dependency Between RGB and Depth

RGB颜色模型 人工智能 计算机科学 依赖关系(UML) 计算机视觉 降噪 噪音(视频) 模式识别(心理学) 图像(数学)
作者
Jun Wang,Peilin Liu,Fei Wen
出处
期刊:IEEE transactions on image processing [Institute of Electrical and Electronics Engineers]
卷期号:32: 159-174 被引量:5
标识
DOI:10.1109/tip.2022.3226419
摘要

Due to the imaging mechanism of time-of-flight (ToF) sensors, the captured depth images usually suffer from severe noise and degradation. Though many RGB-guided methods have been proposed for depth image enhancement in the past few years, yet the enhancement performance on real-world depth images is still largely unsatisfactory. Two main reasons are the complexity of realistic noise and degradation in depth images, and the difficulty in collecting noise-clean pairs for supervised enhancement learning. This work aims to develop a self-supervised learning method for RGB-guided depth image enhancement, which does not require any noisy-clean pairs but can significantly boost the enhancement performance on real-world noisy depth images. To this end, we exploit the dependency between RGB and depth images to self-supervise the learning of the enhancement model. It is achieved by maximizing the cross-modal dependency between RGB and depth to promote the enhanced depth having dependency with the RGB of the same scene as much as possible. Furthermore, we augment the cross-modal dependency maximization formulation based on the optimal transport theory to achieve further performance improvement. Experimental results on both synthetic and real-world data demonstrate that our method can significantly outperform existing state-of-the-art methods on depth denoising, multi-path interference suppression, and hole filling. Particularly, our method shows remarkable superiority over existing ones on real-world data in handling various realistic complex degradation. Code is available at https://github.com/wjcyt/SRDE.
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
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
YuanYechao发布了新的文献求助10
1秒前
现在到未来完成签到,获得积分10
1秒前
隋阳完成签到,获得积分10
1秒前
xusansui321完成签到,获得积分10
2秒前
2秒前
树袋熊发布了新的文献求助100
3秒前
水杯不离手完成签到 ,获得积分10
4秒前
5秒前
5秒前
不配.应助笑点低的傲旋采纳,获得10
5秒前
krajicek完成签到,获得积分10
6秒前
大个应助无敌LI采纳,获得10
6秒前
10秒前
10秒前
11秒前
11秒前
花花完成签到,获得积分10
12秒前
12秒前
春华秋实完成签到,获得积分10
14秒前
云隐完成签到,获得积分10
15秒前
16秒前
山椒发布了新的文献求助10
16秒前
春华秋实发布了新的文献求助10
17秒前
西南楚留香完成签到,获得积分10
17秒前
流沙发布了新的文献求助10
17秒前
充电宝应助Rainbow采纳,获得10
19秒前
19秒前
Wing完成签到 ,获得积分10
19秒前
王佳豪完成签到,获得积分20
19秒前
meng完成签到,获得积分10
19秒前
可乐应助猪爸爸采纳,获得10
20秒前
直率无春发布了新的文献求助10
21秒前
卡卡完成签到,获得积分10
23秒前
25秒前
25秒前
wanci应助Jorna采纳,获得10
26秒前
大个应助科研通管家采纳,获得10
26秒前
劲秉应助科研通管家采纳,获得10
26秒前
小蘑菇应助科研通管家采纳,获得10
26秒前
顾矜应助科研通管家采纳,获得10
26秒前
高分求助中
Spray / Wall-interaction Modelling by Dimensionless Data Analysis 2000
ALA生合成不全マウスでの糖代謝異常の分子機構解析 520
Aspects of Babylonian celestial divination: the lunar eclipse tablets of Enūma Anu Enlil 500
安全防范技术与工程 500
Mathematics and Finite Element Discretizations of Incompressible Navier—Stokes Flows 500
2024 Medicinal Chemistry Reviews 400
Dictionary of socialism 350
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 3193679
求助须知:如何正确求助?哪些是违规求助? 2842647
关于积分的说明 8040252
捐赠科研通 2506753
什么是DOI,文献DOI怎么找? 1339363
科研通“疑难数据库(出版商)”最低求助积分说明 638752
邀请新用户注册赠送积分活动 607379