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
小二郎应助周舟采纳,获得10
刚刚
偏i意气用事完成签到,获得积分10
刚刚
科研張完成签到,获得积分10
1秒前
Lucas应助zzk采纳,获得10
3秒前
yyxmh羽儿完成签到,获得积分10
7秒前
Jasper应助Guke采纳,获得10
7秒前
行宇完成签到,获得积分10
7秒前
管江丽发布了新的文献求助10
9秒前
11秒前
小仙女发布了新的文献求助10
11秒前
叁壹粑粑完成签到,获得积分10
12秒前
13秒前
13秒前
zzk发布了新的文献求助10
16秒前
达达完成签到,获得积分10
17秒前
18秒前
KKLD发布了新的文献求助10
18秒前
研友_VZG7GZ应助yyxmh羽儿采纳,获得10
19秒前
饱满破茧完成签到,获得积分10
19秒前
19秒前
武雨珍完成签到,获得积分10
20秒前
Bobonice完成签到,获得积分10
20秒前
Apricity完成签到,获得积分10
21秒前
21秒前
小月完成签到,获得积分10
22秒前
明白放弃完成签到 ,获得积分10
22秒前
小二郎应助WDS采纳,获得10
23秒前
谋勇兼备完成签到,获得积分10
24秒前
queengause发布了新的文献求助10
24秒前
刘唐荣发布了新的文献求助10
25秒前
25秒前
zzk完成签到,获得积分10
28秒前
34秒前
852应助威武冷雪采纳,获得10
35秒前
35秒前
吃不饱星球球长给我不是大牛的求助进行了留言
36秒前
37秒前
yangting发布了新的文献求助80
39秒前
danielbbbb发布了新的文献求助10
40秒前
善学以致用应助TruelyBe采纳,获得30
42秒前
高分求助中
Evolution 3rd edition 1500
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
Ribozymes and aptamers in the RNA world, and in synthetic biology 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 3180839
求助须知:如何正确求助?哪些是违规求助? 2831074
关于积分的说明 7982863
捐赠科研通 2492963
什么是DOI,文献DOI怎么找? 1329932
科研通“疑难数据库(出版商)”最低求助积分说明 635850
版权声明 602954