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
飘逸访文完成签到,获得积分10
刚刚
赘婿应助排骨炖豆角采纳,获得10
1秒前
勤奋幻柏完成签到,获得积分10
1秒前
专炸油条完成签到 ,获得积分10
1秒前
闪闪镜子完成签到 ,获得积分10
1秒前
naive发布了新的文献求助10
2秒前
2秒前
Albee0907完成签到,获得积分10
3秒前
3秒前
云中完成签到,获得积分10
3秒前
CodeCraft应助小虎采纳,获得10
4秒前
管理想完成签到,获得积分10
4秒前
bkagyin应助fanfan采纳,获得10
5秒前
siwen完成签到,获得积分10
5秒前
7秒前
7秒前
橄榄囚徒完成签到 ,获得积分10
8秒前
8秒前
8秒前
zsg完成签到,获得积分10
8秒前
m彬m彬完成签到 ,获得积分10
8秒前
8秒前
jt完成签到,获得积分10
9秒前
传奇3应助hello采纳,获得10
9秒前
百川发布了新的文献求助10
9秒前
10秒前
搜集达人应助白夜采纳,获得30
10秒前
10秒前
10秒前
华仔应助石火采纳,获得10
11秒前
homelo完成签到,获得积分10
11秒前
11秒前
12秒前
12秒前
12秒前
@-@发布了新的文献求助10
12秒前
SSSYYY完成签到,获得积分10
12秒前
ss13l完成签到,获得积分10
12秒前
Hellowa完成签到,获得积分10
12秒前
tomf完成签到,获得积分10
13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
2024 Medicinal Chemistry Reviews 400
Актуализированная стратиграфическая схема триасовых отложений Прикаспийского региона. Объяснительная записка 360
Dictionary of socialism 350
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 3193012
求助须知:如何正确求助?哪些是违规求助? 2842055
关于积分的说明 8037114
捐赠科研通 2505918
什么是DOI,文献DOI怎么找? 1338749
科研通“疑难数据库(出版商)”最低求助积分说明 638526
邀请新用户注册赠送积分活动 607034