亲爱的研友该休息了!由于当前在线用户较少,发布求助请尽量完整的填写文献信息,科研通机器人24小时在线,伴您度过漫漫科研夜!身体可是革命的本钱,早点休息,好梦!

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
zzb发布了新的文献求助10
1秒前
Jay发布了新的文献求助30
2秒前
9秒前
科研通AI2S应助姚倩倩采纳,获得10
9秒前
12秒前
kkkw发布了新的文献求助30
18秒前
22秒前
27秒前
koh发布了新的文献求助10
28秒前
h0jian09完成签到,获得积分10
29秒前
NexusExplorer应助Jay采纳,获得30
31秒前
Rezeal发布了新的文献求助10
33秒前
58秒前
58秒前
Rezeal关注了科研通微信公众号
1分钟前
1分钟前
1分钟前
Owen应助郜雨寒采纳,获得10
1分钟前
kkkw完成签到,获得积分10
1分钟前
嗯哼举报仧乆求助涉嫌违规
1分钟前
1分钟前
1分钟前
1分钟前
郜雨寒发布了新的文献求助10
1分钟前
Jay发布了新的文献求助30
1分钟前
嗯哼举报RATHER求助涉嫌违规
1分钟前
Tine完成签到,获得积分10
1分钟前
1分钟前
Tine发布了新的文献求助10
2分钟前
syalonyui完成签到,获得积分10
2分钟前
2分钟前
嗯哼举报smiles求助涉嫌违规
2分钟前
2分钟前
2分钟前
段祥发布了新的文献求助10
2分钟前
深情安青应助逗你玩采纳,获得10
2分钟前
无限寻雪完成签到 ,获得积分10
2分钟前
田様应助爱唱歌的yu仔采纳,获得10
2分钟前
顾矜应助ygl0217采纳,获得10
3分钟前
迅速的月光完成签到 ,获得积分10
3分钟前
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
Dictionary of socialism 350
Mixed-anion Compounds 300
Geochemistry, 2nd Edition 地球化学经典教科书第二版 300
Idoxuridine 260
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 3196673
求助须知:如何正确求助?哪些是违规求助? 2845422
关于积分的说明 8054038
捐赠科研通 2509985
什么是DOI,文献DOI怎么找? 1342199
科研通“疑难数据库(出版商)”最低求助积分说明 639320
邀请新用户注册赠送积分活动 608633