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
loin完成签到,获得积分10
刚刚
程哲瀚完成签到,获得积分10
2秒前
zhaoxiaonuan完成签到,获得积分10
5秒前
Ryan完成签到 ,获得积分10
5秒前
zyw完成签到 ,获得积分10
6秒前
glanceofwind完成签到 ,获得积分10
10秒前
点点完成签到 ,获得积分10
11秒前
qks完成签到 ,获得积分10
21秒前
livra1058完成签到,获得积分10
21秒前
不安的松完成签到 ,获得积分10
23秒前
634301059完成签到 ,获得积分10
27秒前
xxxxam完成签到,获得积分10
29秒前
四爷完成签到,获得积分10
30秒前
Tony12完成签到,获得积分10
30秒前
找找找文献完成签到,获得积分10
33秒前
Hello应助哈哈采纳,获得10
33秒前
善良海云完成签到,获得积分10
42秒前
安澜完成签到,获得积分10
42秒前
44秒前
kangwer完成签到,获得积分10
46秒前
研友_CCQ_M完成签到,获得积分10
47秒前
刘刘完成签到 ,获得积分10
49秒前
STH发布了新的文献求助30
49秒前
YYA完成签到 ,获得积分10
56秒前
AJ完成签到 ,获得积分10
1分钟前
alexlpb完成签到,获得积分10
1分钟前
zly完成签到 ,获得积分10
1分钟前
lxcy0612完成签到,获得积分10
1分钟前
1分钟前
稳重傲晴完成签到 ,获得积分10
1分钟前
lbx完成签到,获得积分10
1分钟前
argon完成签到,获得积分10
1分钟前
1分钟前
微笑芒果完成签到 ,获得积分10
1分钟前
初心路完成签到 ,获得积分10
1分钟前
小悦悦完成签到 ,获得积分10
1分钟前
敏感的鼠标完成签到 ,获得积分10
1分钟前
碧蓝丹烟完成签到 ,获得积分10
1分钟前
许多多同学完成签到,获得积分10
1分钟前
HJBF666完成签到 ,获得积分10
1分钟前
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 3190111
求助须知:如何正确求助?哪些是违规求助? 2839415
关于积分的说明 8023597
捐赠科研通 2502244
什么是DOI,文献DOI怎么找? 1336411
科研通“疑难数据库(出版商)”最低求助积分说明 637841
邀请新用户注册赠送积分活动 605974