已入深夜,您辛苦了!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!祝你早点完成任务,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
田様应助科研通管家采纳,获得10
2秒前
科研通AI2S应助科研通管家采纳,获得10
2秒前
慢歌完成签到 ,获得积分10
5秒前
丸子完成签到 ,获得积分10
6秒前
Jemma完成签到 ,获得积分10
6秒前
6秒前
Fairy完成签到 ,获得积分10
6秒前
仙布着急发布了新的文献求助10
10秒前
10秒前
ch发布了新的文献求助10
10秒前
yangzai完成签到 ,获得积分10
13秒前
脑洞疼应助1234567890采纳,获得10
13秒前
feezy完成签到,获得积分10
14秒前
taku发布了新的文献求助10
14秒前
打打应助ely采纳,获得10
17秒前
17秒前
幸运的bella完成签到,获得积分10
18秒前
冷酷愚志完成签到,获得积分10
19秒前
++完成签到 ,获得积分10
20秒前
起风了完成签到 ,获得积分10
22秒前
24秒前
24秒前
taku完成签到,获得积分10
24秒前
1234567890完成签到 ,获得积分10
24秒前
电击信子完成签到 ,获得积分10
25秒前
HY应助112233采纳,获得10
27秒前
camille发布了新的文献求助10
29秒前
29秒前
ely发布了新的文献求助10
30秒前
33秒前
影子完成签到 ,获得积分10
33秒前
好运莲莲发布了新的文献求助10
34秒前
甜美的问蕊完成签到 ,获得积分10
36秒前
1234567890发布了新的文献求助10
39秒前
xona完成签到,获得积分10
39秒前
ely完成签到,获得积分10
40秒前
40秒前
鲤鱼书双发布了新的文献求助10
40秒前
41秒前
CYing完成签到 ,获得积分10
41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
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 3196567
求助须知:如何正确求助?哪些是违规求助? 2845265
关于积分的说明 8053695
捐赠科研通 2509895
什么是DOI,文献DOI怎么找? 1342105
科研通“疑难数据库(出版商)”最低求助积分说明 639304
邀请新用户注册赠送积分活动 608595