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
牛牛发布了新的文献求助10
1秒前
Ruby-Geo完成签到,获得积分10
1秒前
大个应助沉默襄采纳,获得10
1秒前
zjl1112发布了新的文献求助10
3秒前
3秒前
4秒前
科研通AI2S应助牛牛采纳,获得10
5秒前
chenhunhun发布了新的文献求助10
5秒前
6秒前
6秒前
Faith完成签到 ,获得积分10
7秒前
三哥完成签到,获得积分10
8秒前
廿廿廿发布了新的文献求助10
8秒前
小二郎应助求知的秀儿采纳,获得10
9秒前
JamesPei应助皮皮最可爱采纳,获得10
9秒前
Jasper应助nancy采纳,获得10
10秒前
10秒前
10秒前
李玟发布了新的文献求助10
11秒前
zjl1112完成签到,获得积分10
11秒前
11秒前
汉堡包应助GuSiwen采纳,获得10
14秒前
猪瘾犯了发布了新的文献求助10
14秒前
愤怒的觅珍完成签到,获得积分10
14秒前
科目三应助啦啦啦啦啦采纳,获得10
15秒前
迷路的二狗关注了科研通微信公众号
16秒前
安屿发布了新的文献求助10
16秒前
沉静秋尽完成签到,获得积分10
16秒前
Owen应助乐观的如雪采纳,获得10
17秒前
沉默襄发布了新的文献求助10
17秒前
英姑应助虚幻龙猫采纳,获得10
18秒前
18秒前
maomao1986完成签到,获得积分10
18秒前
小马甲应助iY采纳,获得30
19秒前
19秒前
20秒前
20秒前
果同学完成签到,获得积分10
23秒前
23秒前
pitto发布了新的文献求助10
23秒前
高分求助中
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
A new species of Coccus (Homoptera: Coccoidea) from Malawi 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 3183207
求助须知:如何正确求助?哪些是违规求助? 2833396
关于积分的说明 7993630
捐赠科研通 2495497
什么是DOI,文献DOI怎么找? 1331539
科研通“疑难数据库(出版商)”最低求助积分说明 636332
邀请新用户注册赠送积分活动 603496