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
zhangzhangzhang完成签到,获得积分10
2秒前
大白狐狸发布了新的文献求助10
3秒前
qwq发布了新的文献求助10
4秒前
5秒前
文静翠风kop1完成签到,获得积分10
5秒前
fffgz完成签到 ,获得积分10
7秒前
科研通AI2S应助巴达天使采纳,获得10
9秒前
鑫鑫发布了新的文献求助10
10秒前
10秒前
nan完成签到,获得积分10
10秒前
你好呀嘻嘻完成签到 ,获得积分10
13秒前
受伤觅柔完成签到,获得积分10
14秒前
风趣秋白完成签到,获得积分10
15秒前
达达利亚发布了新的文献求助10
15秒前
悦己完成签到,获得积分10
17秒前
斯文败类应助屈狒狒采纳,获得10
18秒前
19秒前
科研通AI2S应助Suchus采纳,获得10
19秒前
21秒前
ewmmel完成签到 ,获得积分10
22秒前
派大星完成签到 ,获得积分10
22秒前
艳艳子完成签到,获得积分10
23秒前
Jasper应助Jiu采纳,获得10
24秒前
yy应助清爽念文采纳,获得10
26秒前
28秒前
Yzz完成签到,获得积分10
33秒前
33秒前
落后翠柏发布了新的文献求助10
34秒前
35秒前
Jiu发布了新的文献求助10
37秒前
37秒前
38秒前
羊大侠发布了新的文献求助10
40秒前
Skylar完成签到,获得积分10
40秒前
寻道图强应助自然的宝贝采纳,获得30
41秒前
风的季节完成签到,获得积分0
42秒前
Jiu完成签到,获得积分10
42秒前
牡丹城跑步的虾完成签到 ,获得积分10
42秒前
友好白凡发布了新的文献求助10
43秒前
43秒前
高分求助中
Spray / Wall-interaction Modelling by Dimensionless Data Analysis 2000
Evolution 3rd edition 1500
Mantiden: Faszinierende Lauerjäger Faszinierende Lauerjäger 700
PraxisRatgeber: Mantiden: Faszinierende Lauerjäger 700
ALA生合成不全マウスでの糖代謝異常の分子機構解析 520
Mathematics and Finite Element Discretizations of Incompressible Navier—Stokes Flows 500
A new species of Coccus (Homoptera: Coccoidea) from Malawi 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 3187521
求助须知:如何正确求助?哪些是违规求助? 2837354
关于积分的说明 8014541
捐赠科研通 2499980
什么是DOI,文献DOI怎么找? 1334671
科研通“疑难数据库(出版商)”最低求助积分说明 637231
邀请新用户注册赠送积分活动 605199