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
FashionBoy应助等等小ur采纳,获得10
刚刚
默默的剑通完成签到,获得积分10
刚刚
谨慎的雍完成签到,获得积分10
1秒前
Dusk大寺柯完成签到 ,获得积分10
1秒前
melenda发布了新的文献求助10
2秒前
科目三应助药不能停采纳,获得10
2秒前
2秒前
刻苦的寻凝完成签到,获得积分10
3秒前
Yao完成签到,获得积分10
3秒前
3秒前
IP190237完成签到,获得积分10
5秒前
若变记忆便迷人关注了科研通微信公众号
6秒前
隐形曼青应助時雨采纳,获得10
7秒前
高高的网络应助简约采纳,获得10
7秒前
清脆安南发布了新的文献求助10
9秒前
拼搏雨竹完成签到 ,获得积分10
9秒前
15秒前
海孩子完成签到,获得积分10
16秒前
16秒前
seven完成签到,获得积分10
17秒前
留胡子的霖完成签到,获得积分10
18秒前
不配.应助eriy采纳,获得10
20秒前
21秒前
時雨发布了新的文献求助10
22秒前
23秒前
Lucas应助阿腾采纳,获得10
24秒前
25秒前
小小完成签到 ,获得积分10
25秒前
ok123完成签到 ,获得积分10
26秒前
Yael发布了新的文献求助10
27秒前
時雨完成签到,获得积分10
28秒前
钱大大完成签到,获得积分10
28秒前
hhhh完成签到 ,获得积分10
29秒前
好好学习完成签到,获得积分20
29秒前
32秒前
桐桐应助超级大定春采纳,获得10
33秒前
脑洞疼应助Yael采纳,获得10
33秒前
大水牛完成签到,获得积分10
34秒前
35秒前
36秒前
高分求助中
Spray / Wall-interaction Modelling by Dimensionless Data Analysis 2000
Evolution 3rd edition 1500
保险藏宝图 1000
Lire en communiste 1000
Mantiden: Faszinierende Lauerjäger Faszinierende Lauerjäger 700
PraxisRatgeber: Mantiden: Faszinierende Lauerjäger 700
Mathematics and Finite Element Discretizations of Incompressible Navier—Stokes Flows 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 3184524
求助须知:如何正确求助?哪些是违规求助? 2834852
关于积分的说明 8001581
捐赠科研通 2497202
什么是DOI,文献DOI怎么找? 1332723
科研通“疑难数据库(出版商)”最低求助积分说明 636663
邀请新用户注册赠送积分活动 604036