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
追着太阳跑完成签到,获得积分20
刚刚
小乐完成签到,获得积分10
1秒前
阿蒙发布了新的文献求助10
3秒前
彭于晏应助雨上悲采纳,获得30
4秒前
4秒前
orixero应助Alarician采纳,获得10
5秒前
6秒前
6秒前
7秒前
ZhiquanYu发布了新的文献求助10
7秒前
刘洋发布了新的文献求助10
9秒前
12秒前
烨霖发布了新的文献求助10
12秒前
个性的振家完成签到,获得积分10
16秒前
19秒前
酷波er应助Yolen LI采纳,获得10
19秒前
小小罗发布了新的文献求助10
19秒前
NexusExplorer应助ZhiquanYu采纳,获得10
20秒前
喏晨完成签到 ,获得积分10
21秒前
无私冰蝶完成签到,获得积分10
23秒前
张努力完成签到,获得积分10
23秒前
24秒前
star完成签到,获得积分10
24秒前
wanci应助柯北采纳,获得10
25秒前
直率心锁完成签到,获得积分10
26秒前
26秒前
27秒前
皮蛋努力科研完成签到 ,获得积分10
27秒前
28秒前
memebao发布了新的文献求助30
28秒前
山水完成签到,获得积分10
28秒前
31秒前
Yolen LI发布了新的文献求助10
31秒前
32秒前
wanci应助李小伟采纳,获得10
32秒前
欣喜易蓉完成签到 ,获得积分10
34秒前
ZhiquanYu完成签到,获得积分10
34秒前
35秒前
烨霖完成签到,获得积分10
36秒前
36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
Mixed-anion Compounds 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 3197881
求助须知:如何正确求助?哪些是违规求助? 2846631
关于积分的说明 8060138
捐赠科研通 2511547
什么是DOI,文献DOI怎么找? 1343447
科研通“疑难数据库(出版商)”最低求助积分说明 639541
邀请新用户注册赠送积分活动 609146