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
嘻嘻哈哈完成签到,获得积分10
1秒前
pp发布了新的文献求助50
1秒前
kkk完成签到 ,获得积分10
1秒前
3秒前
chiuchiu完成签到,获得积分20
3秒前
天锁月痕完成签到,获得积分10
4秒前
4秒前
顺利的乐枫完成签到 ,获得积分10
5秒前
Jasper应助畅快的问枫采纳,获得10
6秒前
6秒前
所所应助周周采纳,获得10
8秒前
8秒前
10秒前
彭于晏应助光亮的世界采纳,获得10
11秒前
12秒前
要减肥发布了新的文献求助50
13秒前
13秒前
大气新烟完成签到 ,获得积分10
13秒前
15秒前
kang12发布了新的文献求助10
16秒前
大白菜心发布了新的文献求助30
16秒前
17秒前
17秒前
18秒前
123完成签到,获得积分10
18秒前
JackMa应助粗心的初蓝采纳,获得10
19秒前
劲秉应助chiuchiu采纳,获得10
20秒前
21秒前
22秒前
寻度发布了新的文献求助10
22秒前
liu123发布了新的文献求助10
23秒前
文光完成签到,获得积分10
24秒前
24秒前
123发布了新的文献求助10
26秒前
26秒前
科研通AI2S应助肾小球呵呵采纳,获得10
28秒前
繁荣的妙旋完成签到,获得积分10
29秒前
茜zi应助liu123采纳,获得10
31秒前
wen发布了新的文献求助10
31秒前
XXin关注了科研通微信公众号
31秒前
高分求助中
Spray / Wall-interaction Modelling by Dimensionless Data Analysis 2000
Evolution 3rd edition 1500
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
2-Acetyl-1-pyrroline: an important aroma component of cooked rice 500
Handbook on People's China (1957) 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 3188644
求助须知:如何正确求助?哪些是违规求助? 2838125
关于积分的说明 8018783
捐赠科研通 2500957
什么是DOI,文献DOI怎么找? 1335264
科研通“疑难数据库(出版商)”最低求助积分说明 637484
邀请新用户注册赠送积分活动 605587