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
hauff发布了新的文献求助10
1秒前
1秒前
2秒前
zho发布了新的文献求助30
2秒前
2秒前
洲洲发布了新的文献求助20
3秒前
3秒前
3秒前
4秒前
5秒前
Leo000007发布了新的文献求助10
7秒前
www发布了新的文献求助30
7秒前
MJQ发布了新的文献求助10
7秒前
CHAIZH发布了新的文献求助10
7秒前
共享精神应助搞怪网络采纳,获得10
7秒前
7秒前
7秒前
陶醉雨兰发布了新的文献求助30
7秒前
8秒前
InfoNinja应助lyp采纳,获得30
8秒前
脑洞疼应助咸蛋超人采纳,获得10
9秒前
9秒前
尊敬曼岚发布了新的文献求助10
9秒前
可爱的函函应助超帅傲白采纳,获得10
10秒前
慵懒闲散山人完成签到,获得积分10
10秒前
happy123完成签到,获得积分10
11秒前
隐形曼青应助优雅毛豆采纳,获得10
11秒前
落寞代亦完成签到,获得积分10
11秒前
yuting发布了新的文献求助10
11秒前
坚强的隶完成签到,获得积分10
12秒前
12秒前
ziyu完成签到,获得积分10
12秒前
myt完成签到 ,获得积分10
13秒前
沈高腾完成签到,获得积分10
13秒前
搜集达人应助流浪采纳,获得10
14秒前
哈米伯伯完成签到 ,获得积分10
14秒前
wangzh发布了新的文献求助10
14秒前
丘比特应助CHAIZH采纳,获得10
14秒前
16秒前
16秒前
高分求助中
Evolution 3rd edition 1500
保险藏宝图 1000
Lire en communiste 1000
Mantiden: Faszinierende Lauerjäger Faszinierende Lauerjäger 700
PraxisRatgeber: Mantiden: Faszinierende Lauerjäger 700
A new species of Coccus (Homoptera: Coccoidea) from Malawi 500
2-Acetyl-1-pyrroline: an important aroma component of cooked rice 500
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 3181459
求助须知:如何正确求助?哪些是违规求助? 2831701
关于积分的说明 7986194
捐赠科研通 2493698
什么是DOI,文献DOI怎么找? 1330255
科研通“疑难数据库(出版商)”最低求助积分说明 635954
版权声明 602955