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
1111完成签到,获得积分10
刚刚
不配.应助yan采纳,获得20
刚刚
2秒前
didi完成签到,获得积分10
4秒前
咕噜噜噜噜应助xudonghui采纳,获得10
5秒前
CodeCraft应助林七七采纳,获得10
5秒前
5秒前
Spiderman发布了新的文献求助10
7秒前
9秒前
QinGY完成签到,获得积分10
9秒前
pcf发布了新的文献求助10
9秒前
半个柚子完成签到 ,获得积分10
9秒前
szh123发布了新的文献求助10
9秒前
DDD完成签到,获得积分10
10秒前
自觉问梅完成签到,获得积分10
11秒前
14秒前
14秒前
15秒前
逢投必中发布了新的文献求助30
16秒前
情怀应助内向钻石采纳,获得10
18秒前
Hello应助洗澡记得戴浴帽采纳,获得20
18秒前
shenmizhe发布了新的文献求助10
18秒前
华仔应助pcf采纳,获得10
19秒前
天天快乐应助听弦采纳,获得10
19秒前
情怀应助可耐的盼秋采纳,获得10
19秒前
任性机器猫完成签到,获得积分10
20秒前
英姑应助小易采纳,获得10
20秒前
Ke发布了新的文献求助10
20秒前
21秒前
852应助lbyscu采纳,获得10
23秒前
Lynn应助任性机器猫采纳,获得10
24秒前
cami119关注了科研通微信公众号
25秒前
zrj发布了新的文献求助20
26秒前
28秒前
28秒前
阿啵呲嘚关注了科研通微信公众号
32秒前
听弦发布了新的文献求助10
33秒前
orixero应助姚盈盈采纳,获得10
33秒前
33秒前
34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
A new species of Coccus (Homoptera: Coccoidea) from Malawi 500
2-Acetyl-1-pyrroline: an important aroma component of cooked rice 500
A real-time energy management strategy based on fuzzy control and ECMS for PHEVs 400
Handbook on People's China (1957) 400
2024 Medicinal Chemistry Reviews 400
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 3189479
求助须知:如何正确求助?哪些是违规求助? 2838800
关于积分的说明 8021619
捐赠科研通 2501710
什么是DOI,文献DOI怎么找? 1335920
科研通“疑难数据库(出版商)”最低求助积分说明 637731
邀请新用户注册赠送积分活动 605810