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
李爱国应助科研小小小白采纳,获得10
刚刚
ding应助独特的绯采纳,获得10
2秒前
完美世界应助上杉绘梨衣采纳,获得10
4秒前
4秒前
sora98完成签到 ,获得积分10
6秒前
星辰大海应助彩虹屁篓子采纳,获得10
7秒前
8秒前
9秒前
9秒前
科研通AI2S应助易楠采纳,获得10
10秒前
11秒前
xiao完成签到,获得积分10
12秒前
香蕉觅云应助SupppperZIP采纳,获得10
13秒前
zt发布了新的文献求助10
13秒前
zhangshuang发布了新的文献求助30
15秒前
路过完成签到,获得积分10
15秒前
Jasper应助强健的皮皮虾采纳,获得10
15秒前
领导范儿应助yinyin采纳,获得10
16秒前
17秒前
18秒前
..完成签到 ,获得积分10
18秒前
18秒前
科研通AI2S应助彤彤采纳,获得10
21秒前
哄哄发布了新的文献求助10
24秒前
bkagyin应助ppppppp_76采纳,获得10
26秒前
27秒前
彩虹屁篓子完成签到 ,获得积分10
27秒前
28秒前
zzzz发布了新的文献求助10
33秒前
无聊的大喇叭完成签到,获得积分10
33秒前
阳尧完成签到,获得积分10
34秒前
34秒前
38秒前
39秒前
41秒前
ppplll发布了新的文献求助10
42秒前
科目三应助DaFei采纳,获得10
42秒前
43秒前
kkdkg发布了新的文献求助10
47秒前
程11完成签到 ,获得积分10
49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 3185603
求助须知:如何正确求助?哪些是违规求助? 2835920
关于积分的说明 8007055
捐赠科研通 2498476
什么是DOI,文献DOI怎么找? 1333472
科研通“疑难数据库(出版商)”最低求助积分说明 636868
邀请新用户注册赠送积分活动 604607