Virtual Mirrors: Non-Line-of-Sight Imaging Beyond the Third Bounce
Diego Royo, Talha Sultan, Adolfo Muñoz, Khadijeh Masumnia-Bisheh, Eric Brandt, Diego Gutierrez, Andreas Velten, Julio Marco
Abstract
Non-line-of-sight (NLOS) imaging methods are capable of reconstructing complex scenes that are not visible to an observer using indirect illumination. However, they assume only third-bounce illumination, so they are currently limited to single-corner configurations, and present limited visibility when imaging surfaces at certain orientations. To reason about and tackle these limitations, we make the key observation that planar diffuse surfaces behave specularly at wavelengths used in the computational wave-based NLOS imaging domain. We call such surfaces virtual mirrors. We leverage this observation to expand the capabilities of NLOS imaging using illumination beyond the third bounce, addressing two problems: imaging single-corner objects at limited visibility angles, and imaging objects hidden behind two corners. To image objects at limited visibility angles, we first analyze the reflections of the known illuminated point on surfaces of the scene as an estimator of the position and orientation of objects with limited visibility. We then image those limited visibility objects by computationally building secondary apertures at other surfaces that observe the target object from a direct visibility perspective. Beyond single-corner NLOS imaging, we exploit the specular behavior of virtual mirrors to image objects hidden behind a second corner by imaging the space behind such virtual mirrors, where the mirror image of objects hidden around two corners is formed. No specular surfaces were involved in the making of this paper.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Cited by top-tier papers3
- Around the Corner mmWave Imaging in Practical EnvironmentsLaura Dodds, Hailan Shanbhag, Junfeng Guan, Saurabh Gupta et al.MobiCom 2024 · 21 citations
- X-band Radar Non-Line-of-Sight ImagingDongyu Du, Mingkun Zhao, Yutong Yang, Dominik Scheuble et al.CVPR 2026 · 1 citation
- Neural Inverse Rendering from Propagating LightAnagh Malik, Benjamin Attal, Andrew Xie, Matthew O'Toole et al.CVPR 2025
Builds on3
- Convolutional Approximations to the General Non-Line-of-Sight Imaging OperatorByeongjoo Ahn, Akshat Dave, Ashok Veeraraghavan, Ioannis Gkioulekas et al.ICCV 2019 · 67 citations
- Virtual light transport matrices for non-line-of-sight imagingJulio Marco, Adrián Jarabo, Ji Hyun Nam, Xiaochun Liu et al.ICCV 2021 · 18 citations
- Seeing Around Street Corners: Non-Line-of-Sight Detection and Tracking In-the-Wild Using Doppler RadarNicolas Scheiner, Florian Kraus, Fangyin Wei, Buu Phan et al.CVPR 2020
Related papers
- Non-Line-of-Sight 3D Reconstruction with RadarHaowen Lai, Zitong Lan, Mingmin ZhaoNeurIPS 2025 · 11 citations
- NLOST: Non-Line-of-Sight Imaging with TransformerYue Li, Jiayong Peng, Juntian Ye, Yueyi Zhang et al.CVPR 2023
- Generalizable Non-Line-of-Sight Imaging with Learnable Physical PriorsShida Sun, Yue Li, Yueyi Zhang, Zhiwei XiongICCV 2025 · 4 citations
- Enhancing Non-line-of-sight Imaging via Learnable Inverse Kernel and Attention MechanismsYanhua Yu, Siyuan Shen, Zi Wang, Binbin Huang et al.ICCV 2023 · 19 citations
- Virtual Scanning: Unsupervised Non-line-of-sight Imaging from Irregularly Undersampled TransientsXingyu Cui, Huanjing Yue, Song Li, Xiangjun Yin et al.NeurIPS 2024 · 13 citations
