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
文艺的明杰完成签到,获得积分10
1秒前
领导范儿应助吱吱采纳,获得10
2秒前
赖向珊发布了新的文献求助10
2秒前
2秒前
陈独秀完成签到,获得积分10
5秒前
momo完成签到,获得积分10
9秒前
ttt关闭了ttt文献求助
9秒前
9秒前
Akim应助yum采纳,获得10
11秒前
12秒前
芝士球球应助rakuyo采纳,获得10
12秒前
多喝水发布了新的文献求助10
12秒前
momo发布了新的文献求助10
13秒前
14秒前
RenZhiyong完成签到,获得积分10
15秒前
16秒前
17秒前
共享精神应助小鱼采纳,获得10
20秒前
李管我完成签到 ,获得积分10
21秒前
柒柒发布了新的文献求助10
21秒前
123发布了新的文献求助10
22秒前
22秒前
我是老大应助Morpheus采纳,获得30
27秒前
islanddd发布了新的文献求助20
28秒前
Orange应助该房地产个人的采纳,获得10
29秒前
李七七完成签到,获得积分10
31秒前
现代的诗槐应助柒柒采纳,获得10
32秒前
32秒前
33秒前
35秒前
37秒前
感动绫完成签到,获得积分10
39秒前
听说你还在搞什么原创完成签到 ,获得积分10
39秒前
39秒前
慕青应助贰叁采纳,获得10
40秒前
无辜紫菜完成签到 ,获得积分10
40秒前
41秒前
万能图书馆应助鲁大师采纳,获得10
41秒前
Yuxin完成签到,获得积分10
43秒前
43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 3185754
求助须知:如何正确求助?哪些是违规求助? 2836018
关于积分的说明 8007337
捐赠科研通 2498516
什么是DOI,文献DOI怎么找? 1333527
科研通“疑难数据库(出版商)”最低求助积分说明 636881
邀请新用户注册赠送积分活动 604637