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
师傅被妖怪抓走了完成签到,获得积分10
1秒前
查文献的小橙完成签到 ,获得积分10
2秒前
3秒前
3秒前
pickle发布了新的文献求助10
3秒前
3秒前
所所应助haapy采纳,获得10
3秒前
不配.应助Cassie采纳,获得50
3秒前
xiaoma发布了新的文献求助10
4秒前
4秒前
布吉岛完成签到,获得积分10
4秒前
NexusExplorer应助我爱学习采纳,获得10
5秒前
mofan发布了新的文献求助10
5秒前
落后书竹发布了新的文献求助10
5秒前
5秒前
飘着的鬼完成签到,获得积分10
6秒前
6秒前
6秒前
学术屎壳郎完成签到,获得积分10
6秒前
敏感的钢铁侠关注了科研通微信公众号
6秒前
不配.应助饱满丹亦采纳,获得10
7秒前
SSS发布了新的文献求助10
8秒前
REBACK完成签到,获得积分20
8秒前
hxksxc完成签到 ,获得积分10
8秒前
孤独无极发布了新的文献求助10
9秒前
9秒前
zxs完成签到,获得积分10
9秒前
是风动发布了新的文献求助10
10秒前
彭于晏应助脸脸采纳,获得10
10秒前
今天吃什么完成签到,获得积分10
11秒前
高高诗柳发布了新的文献求助10
12秒前
研友_85Y5z8发布了新的文献求助10
12秒前
12秒前
14秒前
细腻的老九应助HC采纳,获得10
15秒前
15秒前
不配.应助汤博森采纳,获得10
16秒前
17秒前
17秒前
阿巴理完成签到,获得积分10
19秒前
高分求助中
Spray / Wall-interaction Modelling by Dimensionless Data Analysis 2000
Write Like a Chemist: A Guide and Resource (第二版) 600
Mixed-anion Compounds 600
A new species of Velataspis (Hemiptera Coccoidea Diaspididae) from tea in Assam 500
Earth System Geophysics 500
Aspects of Babylonian celestial divination: the lunar eclipse tablets of Enūma Anu Enlil 500
Geochemistry, 2nd Edition 地球化学经典教科书第二版 401
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 3199603
求助须知:如何正确求助?哪些是违规求助? 2848445
关于积分的说明 8067992
捐赠科研通 2513121
什么是DOI,文献DOI怎么找? 1345678
科研通“疑难数据库(出版商)”最低求助积分说明 640093
邀请新用户注册赠送积分活动 609772