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
meredith0571完成签到,获得积分10
1秒前
1秒前
Young发布了新的文献求助10
3秒前
慕青应助JET_Li采纳,获得10
3秒前
737发布了新的文献求助10
3秒前
3秒前
4秒前
完美世界应助平淡菲音采纳,获得10
5秒前
狗大王发布了新的文献求助10
6秒前
仰望星空发布了新的文献求助10
7秒前
Fan发布了新的文献求助10
7秒前
maction应助江湖樊南生采纳,获得10
9秒前
小曾完成签到,获得积分10
9秒前
10秒前
10秒前
ooseabiscuit发布了新的文献求助10
11秒前
11秒前
JET_Li完成签到,获得积分10
12秒前
12秒前
13秒前
ampm发布了新的文献求助10
13秒前
优秀醉易完成签到 ,获得积分10
14秒前
14秒前
Fan完成签到,获得积分10
15秒前
15秒前
细腻沛萍发布了新的文献求助10
15秒前
JET_Li发布了新的文献求助10
15秒前
ibaji发布了新的文献求助10
15秒前
连名语发布了新的文献求助10
18秒前
19秒前
KK完成签到,获得积分10
20秒前
susuna完成签到,获得积分10
20秒前
抄手爱吃皮完成签到 ,获得积分10
21秒前
平淡菲音发布了新的文献求助10
23秒前
科研小白一枚完成签到,获得积分10
23秒前
737完成签到,获得积分10
25秒前
小张发布了新的文献求助10
25秒前
细腻沛萍完成签到,获得积分10
26秒前
Akim应助连名语采纳,获得10
26秒前
香蕉觅云应助小小采纳,获得10
27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
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
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 3193752
求助须知:如何正确求助?哪些是违规求助? 2842787
关于积分的说明 8040747
捐赠科研通 2506857
什么是DOI,文献DOI怎么找? 1339400
科研通“疑难数据库(出版商)”最低求助积分说明 638755
邀请新用户注册赠送积分活动 607527