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
VPN不好用发布了新的文献求助10
刚刚
蒋羊羊发布了新的文献求助10
1秒前
yjf完成签到,获得积分10
1秒前
2秒前
JamesPei应助轻松乐枫采纳,获得10
2秒前
不倦应助湘澜采纳,获得10
2秒前
大宇完成签到,获得积分10
2秒前
Jasper应助yaya采纳,获得10
3秒前
5秒前
vagrant1131完成签到,获得积分10
6秒前
Satoru发布了新的文献求助10
7秒前
zho应助sunny采纳,获得10
7秒前
了了了发布了新的文献求助10
8秒前
9秒前
111111发布了新的文献求助10
10秒前
希望天下0贩的0应助葵葵采纳,获得10
10秒前
Akim应助清爽的梦菡采纳,获得10
11秒前
11秒前
李健应助小栖是菇凉采纳,获得10
11秒前
苗条的成仁完成签到 ,获得积分10
12秒前
precious完成签到,获得积分10
12秒前
Satoru完成签到,获得积分10
13秒前
轻松乐枫发布了新的文献求助10
14秒前
bkagyin应助了了了采纳,获得30
14秒前
科目三应助科研小小小白采纳,获得10
15秒前
16秒前
16秒前
甄不错发布了新的文献求助10
16秒前
16秒前
17秒前
天天快乐应助杀殿采纳,获得10
19秒前
20秒前
21秒前
22秒前
赘婿应助qqqq采纳,获得10
22秒前
慕青应助TomatoRin采纳,获得30
22秒前
CodeCraft应助VPN不好用采纳,获得10
23秒前
不倦应助当时只道是寻常采纳,获得10
24秒前
25秒前
25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 3181753
求助须知:如何正确求助?哪些是违规求助? 2832076
关于积分的说明 7987660
捐赠科研通 2493961
什么是DOI,文献DOI怎么找? 1330560
科研通“疑难数据库(出版商)”最低求助积分说明 635984
版权声明 602955