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
lijiayu发布了新的文献求助10
刚刚
1秒前
1秒前
慕青应助qcck采纳,获得10
2秒前
CodeCraft应助yyy采纳,获得10
2秒前
科研通AI2S应助ll采纳,获得10
2秒前
风中冰岚发布了新的文献求助10
3秒前
羊咩咩哒完成签到,获得积分10
4秒前
共享精神应助orange9采纳,获得10
4秒前
5秒前
iu发布了新的文献求助10
5秒前
熏香澡牝完成签到,获得积分10
6秒前
reck发布了新的文献求助10
6秒前
yang完成签到,获得积分10
7秒前
牛司发布了新的文献求助10
9秒前
果粒橙完成签到 ,获得积分10
9秒前
丘比特应助心随以动采纳,获得10
10秒前
10秒前
花生豆关注了科研通微信公众号
10秒前
11秒前
shanshan完成签到,获得积分10
11秒前
liy41完成签到 ,获得积分10
12秒前
13秒前
巽风发布了新的文献求助20
13秒前
13秒前
狂野猕猴桃完成签到 ,获得积分10
13秒前
14秒前
dhhaoyihong完成签到,获得积分20
14秒前
古月方源发布了新的文献求助10
14秒前
orange9发布了新的文献求助10
15秒前
细心怜寒发布了新的文献求助10
16秒前
17秒前
17秒前
yyy发布了新的文献求助10
18秒前
newnew完成签到,获得积分10
19秒前
19秒前
ccc发布了新的文献求助10
19秒前
dhhaoyihong发布了新的文献求助10
20秒前
坚定的安双完成签到 ,获得积分20
20秒前
乐乐应助HELIXIA采纳,获得10
21秒前
高分求助中
Spray / Wall-interaction Modelling by Dimensionless Data Analysis 2000
Aspects of Babylonian celestial divination: the lunar eclipse tablets of Enūma Anu Enlil 500
Mathematics and Finite Element Discretizations of Incompressible Navier—Stokes Flows 500
2024 Medicinal Chemistry Reviews 400
Dictionary of socialism 350
Mixed-anion Compounds 300
Geochemistry, 2nd Edition 地球化学经典教科书第二版 300
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 3195192
求助须知:如何正确求助?哪些是违规求助? 2844065
关于积分的说明 8048190
捐赠科研通 2508518
什么是DOI,文献DOI怎么找? 1340876
科研通“疑难数据库(出版商)”最低求助积分说明 639045
邀请新用户注册赠送积分活动 608013