Enhancing Non-line-of-sight Imaging via Learnable Inverse Kernel and Attention Mechanisms

doi:10.1109/ICCV51070.2023.00969

	Enhancing Non-line-of-sight Imaging via Learnable Inverse Kernel and Attention Mechanisms
	Yanhua Yu; Siyuan Shen; Zi Wang; Binbin Huang; Yuehan Wang; Xingyue Peng; Suan Xia; Ping Liu; Ruiqian Li; Shiying Li
	2023-10
会议录名称	2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)
ISSN	1550-5499
页码	10529-10539
发表状态	已发表
DOI	10.1109/ICCV51070.2023.00969
摘要	Recovering information from non-line-of-sight (NLOS) imaging is a computationally-intensive inverse problem. Most physics-based NLOS imaging methods address the complexity of this problem by assuming three-bounce reflections and no self-occlusion. However, these assumptions may break down for objects with large depth variations, preventing physics-based algorithms from accurately reconstructing the details and high-frequency information. On the other hand, while learning-based methods can avoid these assumptions, they may struggle to reconstruct details without specific designs due to the spectral bias of neural networks. To overcome these issues, we propose a novel approach that enhances physics-based NLOS imaging methods by introducing a learnable inverse kernel in the Fourier domain and using an attention mechanism to improve the neural network to learn high-frequency information. Our method is evaluated on publicly available and new synthetic datasets, demonstrating its commendable performance compared to prior physics-based and learning-based methods, especially for objects with large depth variations. Moreover, our approach generalizes well to real data and can be applied to tasks such as classification and depth reconstruction. We will make our code and dataset publicly available: https://sci2020.github.io. © 2023 IEEE.
关键词	Learning systems Training Inverse problems Neural networks Imaging Reflection Kernel
会议名称	2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023
会议地点	Paris, France
会议日期	1-6 Oct. 2023
URL	查看原文
收录类别	EI
语种	英语
出版者	Institute of Electrical and Electronics Engineers Inc.
EI入藏号	20241215793281
原始文献类型	Conference article (CA)
来源库	IEEE
引用统计	正在获取...
文献类型	会议论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/354921
专题	信息科学与技术学院信息科学与技术学院_PI研究组_虞晶怡组信息科学与技术学院_硕士生信息科学与技术学院_博士生
作者单位	Shanghai Engineering Research Center of Intelligent Vision and Imaging, School of Information Science and Technology, ShanghaiTech University, Shanghai, China
第一作者单位	信息科学与技术学院
第一作者的第一单位	信息科学与技术学院
推荐引用方式 GB/T 7714	Yanhua Yu,Siyuan Shen,Zi Wang,et al. Enhancing Non-line-of-sight Imaging via Learnable Inverse Kernel and Attention Mechanisms[C]:Institute of Electrical and Electronics Engineers Inc.,2023:10529-10539.