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
2秒前
高高大地发布了新的文献求助20
2秒前
db完成签到,获得积分10
2秒前
远了个方发布了新的文献求助10
3秒前
3秒前
4秒前
4秒前
小泉完成签到,获得积分10
6秒前
咩咩发布了新的文献求助10
8秒前
自由背包发布了新的文献求助10
9秒前
sette完成签到,获得积分10
10秒前
11秒前
如意的向彤完成签到,获得积分10
11秒前
不万能测光表完成签到,获得积分10
11秒前
王灰灰1完成签到 ,获得积分10
14秒前
14秒前
Jasper应助璀璨c采纳,获得10
15秒前
天机鲁比发布了新的文献求助10
15秒前
Darkangel发布了新的文献求助10
17秒前
18秒前
FYW发布了新的文献求助10
18秒前
lara发布了新的文献求助10
18秒前
18秒前
18秒前
Yziii应助白华苍松采纳,获得20
20秒前
FashionBoy应助冷艳的海白采纳,获得10
21秒前
最近不写作业完成签到,获得积分10
22秒前
充电宝应助Falcon采纳,获得10
22秒前
阳和启蛰完成签到 ,获得积分10
24秒前
风思雅完成签到,获得积分10
26秒前
27秒前
打打应助X_F采纳,获得10
29秒前
小蘑菇应助宁帅采纳,获得10
31秒前
我不是丑橘完成签到,获得积分10
32秒前
王饱饱发布了新的文献求助10
32秒前
彭于彦祖应助paper采纳,获得30
36秒前
frap完成签到,获得积分10
38秒前
天机鲁比完成签到,获得积分20
40秒前
奋斗完成签到 ,获得积分10
41秒前
yhchen发布了新的文献求助20
42秒前
高分求助中
Spray / Wall-interaction Modelling by Dimensionless Data Analysis 2000
Mathematics and Finite Element Discretizations of Incompressible Navier—Stokes Flows 500
2024 Medicinal Chemistry Reviews 400
Dictionary of socialism 350
Mixed-anion Compounds 300
Geochemistry, 2nd Edition 地球化学经典教科书第二版 300
Idoxuridine 260
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 3195050
求助须知:如何正确求助?哪些是违规求助? 2843967
关于积分的说明 8047419
捐赠科研通 2508360
什么是DOI,文献DOI怎么找? 1340757
科研通“疑难数据库(出版商)”最低求助积分说明 639022
邀请新用户注册赠送积分活动 607977