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
刚刚
李健的粉丝团团长应助LHYX采纳,获得10
1秒前
张八完成签到 ,获得积分10
1秒前
在水一方应助愤怒的千凝采纳,获得30
1秒前
2秒前
zhao完成签到 ,获得积分10
3秒前
打工人完成签到,获得积分10
4秒前
jklwss完成签到,获得积分10
4秒前
4秒前
赘婿应助科研通管家采纳,获得10
5秒前
搜集达人应助科研通管家采纳,获得10
5秒前
上官若男应助科研通管家采纳,获得10
5秒前
科研通AI2S应助科研通管家采纳,获得10
5秒前
英俊的铭应助科研通管家采纳,获得10
5秒前
Owen应助科研通管家采纳,获得10
5秒前
彭于晏应助科研通管家采纳,获得10
5秒前
汉堡包应助科研通管家采纳,获得10
5秒前
NexusExplorer应助科研通管家采纳,获得10
5秒前
杳鸢应助科研通管家采纳,获得10
6秒前
科研通AI2S应助科研通管家采纳,获得10
6秒前
烟花应助科研通管家采纳,获得10
6秒前
科研通AI2S应助科研通管家采纳,获得10
6秒前
NexusExplorer应助科研通管家采纳,获得10
6秒前
隐形曼青应助科研通管家采纳,获得10
6秒前
6秒前
7秒前
7秒前
7秒前
7秒前
神金发布了新的文献求助10
7秒前
7秒前
科研通AI2S应助赵teng采纳,获得10
7秒前
CipherSage应助赵teng采纳,获得10
7秒前
百里瓶窑发布了新的文献求助10
7秒前
jjk发布了新的文献求助10
10秒前
心想事陈完成签到 ,获得积分10
11秒前
如意完成签到,获得积分10
12秒前
LHYX发布了新的文献求助10
13秒前
浮生发布了新的文献求助10
13秒前
百里瓶窑完成签到,获得积分10
17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
安全防范技术与工程 500
Mathematics and Finite Element Discretizations of Incompressible Navier—Stokes Flows 500
A real-time energy management strategy based on fuzzy control and ECMS for PHEVs 400
2024 Medicinal Chemistry Reviews 400
Актуализированная стратиграфическая схема триасовых отложений Прикаспийского региона. Объяснительная записка 360
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 3191785
求助须知:如何正确求助?哪些是违规求助? 2841150
关于积分的说明 8031512
捐赠科研通 2504591
什么是DOI,文献DOI怎么找? 1337873
科研通“疑难数据库(出版商)”最低求助积分说明 638205
邀请新用户注册赠送积分活动 606711