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
小王完成签到,获得积分10
3秒前
123完成签到,获得积分10
3秒前
吴雨峰完成签到,获得积分10
4秒前
wtbxsjy完成签到,获得积分10
4秒前
栗子应助sean采纳,获得10
4秒前
激情的一斩完成签到,获得积分20
6秒前
马玉祥发布了新的文献求助10
7秒前
7秒前
wyy应助66666天采纳,获得10
7秒前
Lee发布了新的文献求助10
7秒前
劲秉应助elooo采纳,获得10
8秒前
lll完成签到,获得积分20
8秒前
英俊的铭应助zzz采纳,获得10
9秒前
10秒前
LSY发布了新的文献求助10
10秒前
田様应助拂晓采纳,获得10
10秒前
英姑应助自信鑫鹏采纳,获得10
12秒前
小匹夫完成签到,获得积分10
12秒前
加菲丰丰应助激情的一斩采纳,获得20
13秒前
普普完成签到 ,获得积分10
13秒前
诺之发布了新的文献求助10
13秒前
14秒前
14秒前
顾矜应助Edison采纳,获得10
16秒前
16秒前
思源应助cc采纳,获得10
18秒前
youmuyou完成签到,获得积分10
18秒前
解师发布了新的文献求助10
19秒前
机智乐蕊完成签到,获得积分10
21秒前
ured发布了新的文献求助10
22秒前
李鱼丸发布了新的文献求助10
22秒前
劲秉应助白华苍松采纳,获得20
24秒前
25秒前
25秒前
26秒前
英俊的铭应助yystudy采纳,获得10
26秒前
Apollonia完成签到 ,获得积分10
27秒前
Lz完成签到,获得积分10
27秒前
Jasper应助乔心采纳,获得10
28秒前
28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
Mathematics and Finite Element Discretizations of Incompressible Navier—Stokes Flows 500
A new species of Coccus (Homoptera: Coccoidea) from Malawi 500
2-Acetyl-1-pyrroline: an important aroma component of cooked rice 500
A real-time energy management strategy based on fuzzy control and ECMS for PHEVs 400
Handbook on People's China (1957) 400
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 3189290
求助须知:如何正确求助?哪些是违规求助? 2838673
关于积分的说明 8020919
捐赠科研通 2501536
什么是DOI,文献DOI怎么找? 1335703
科研通“疑难数据库(出版商)”最低求助积分说明 637678
邀请新用户注册赠送积分活动 605774