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
刚刚
阿湛发布了新的文献求助10
1秒前
柠檬酸应助abcjin采纳,获得10
1秒前
hoo完成签到 ,获得积分10
2秒前
仂尤发布了新的文献求助10
2秒前
2秒前
安静的半蕾完成签到,获得积分10
3秒前
斯尼奇完成签到,获得积分10
3秒前
烟花应助jiacheng采纳,获得10
3秒前
3秒前
3秒前
5秒前
5秒前
5秒前
无花果应助风趣的绮露采纳,获得10
5秒前
领导范儿应助喜悦寒凝采纳,获得10
6秒前
华仔应助ihuu采纳,获得30
6秒前
6秒前
7秒前
siwen完成签到,获得积分10
7秒前
123完成签到,获得积分10
7秒前
7秒前
8秒前
8秒前
zhangz完成签到,获得积分10
8秒前
乐乐发布了新的文献求助10
8秒前
小宝爸爸发布了新的文献求助10
8秒前
好多鱼完成签到 ,获得积分10
9秒前
果果完成签到,获得积分10
9秒前
zqqq发布了新的文献求助10
10秒前
缓慢的从寒完成签到,获得积分10
10秒前
10秒前
10秒前
悲凉的冬天完成签到,获得积分10
10秒前
11秒前
11秒前
热心芷烟完成签到,获得积分10
11秒前
慕青应助博士采纳,获得10
11秒前
13秒前
顺心季节完成签到,获得积分10
13秒前
高分求助中
Spray / Wall-interaction Modelling by Dimensionless Data Analysis 2000
Femoral insertion of the ACL. Radiographic quadrant method 1000
ALA生合成不全マウスでの糖代謝異常の分子機構解析 520
Mathematics and Finite Element Discretizations of Incompressible Navier—Stokes Flows 500
2024 Medicinal Chemistry Reviews 400
Dictionary of socialism 350
Geochemistry, 2nd Edition 地球化学经典教科书第二版 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 3194546
求助须知:如何正确求助?哪些是违规求助? 2843443
关于积分的说明 8045113
捐赠科研通 2507901
什么是DOI,文献DOI怎么找? 1340273
科研通“疑难数据库(出版商)”最低求助积分说明 638909
邀请新用户注册赠送积分活动 607780