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
Sci完成签到,获得积分10
刚刚
haha发布了新的文献求助10
1秒前
纱夏完成签到,获得积分10
1秒前
Ava应助dengge采纳,获得10
1秒前
1秒前
一只饿晕的猪应助野风车采纳,获得10
1秒前
1秒前
2秒前
尹冰之完成签到,获得积分10
2秒前
GYL完成签到,获得积分10
2秒前
时光发布了新的文献求助10
2秒前
鲜艳的手链完成签到,获得积分10
3秒前
minatozaki完成签到,获得积分10
3秒前
迅速的萧完成签到 ,获得积分10
3秒前
3秒前
忧郁的续发布了新的文献求助10
3秒前
3秒前
闵仇天完成签到,获得积分10
3秒前
CHEN.CHENG完成签到,获得积分10
4秒前
一二完成签到,获得积分10
4秒前
4秒前
5秒前
hi完成签到 ,获得积分10
5秒前
柠檬完成签到 ,获得积分10
5秒前
lzy发布了新的文献求助10
6秒前
6秒前
Gorge完成签到,获得积分10
6秒前
糯糯发布了新的文献求助10
6秒前
6秒前
hyl-tcm发布了新的文献求助10
7秒前
隐形曼青应助于某人采纳,获得10
7秒前
百里丶妍完成签到,获得积分10
7秒前
zyq完成签到 ,获得积分10
7秒前
22发布了新的文献求助10
7秒前
小马甲应助友好若南采纳,获得10
7秒前
蜗牛的世界完成签到,获得积分10
7秒前
manchang完成签到 ,获得积分10
8秒前
hulin_zjxu发布了新的文献求助10
8秒前
研友_Z1WrgL发布了新的文献求助10
8秒前
卢敏明发布了新的文献求助10
8秒前
高分求助中
Write Like a Chemist: A Guide and Resource (第二版) 600
Mixed-anion Compounds 600
Language injustice and social equity in EMI policies in China 500
A new species of Velataspis (Hemiptera Coccoidea Diaspididae) from tea in Assam 500
Earth System Geophysics 500
Aspects of Babylonian celestial divination: the lunar eclipse tablets of Enūma Anu Enlil 500
Geochemistry, 2nd Edition 地球化学经典教科书第二版 401
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 3201393
求助须知:如何正确求助?哪些是违规求助? 2850949
关于积分的说明 8075746
捐赠科研通 2514904
什么是DOI,文献DOI怎么找? 1347541
科研通“疑难数据库(出版商)”最低求助积分说明 640457
邀请新用户注册赠送积分活动 610650