Coherence as Texture - Passive Textureless 3D Reconstruction by Self-Interference
Wei-Yu Chen, Aswin C. Sankaranarayanan, Anat Levin, Matthew O'Toole
摘要
Passive depth estimation based on stereo or defocus relies on the presence of the texture on an object to resolve its depth. Hence, recovering the depth of a textureless objectfor example, a large white wall-is not just hard but perhaps even impossible. Or is it? We show that spatial coherence, a property of natural light sources, can be used to resolve the depth of a scene point even when it is textureless. Our approach relies on the idea that natural light scattered off a scene point is locally coherent with itself, while incoherent with the light scattered from other surface points; we use this insight to design an optical setup that uses selfinterference as a texture feature for estimating depth. Our lab prototype is capable of resolving depths of textureless objects in sunlight as well as indoor lights.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper1
- Opportunistic Single-Photon Time of FlightSotiris Nousias, Mian Wei, Howard Xiao, Maxx Wu 等CVPR 2025
它引用的顶会 Paper3
- Interferometric transmission probing with coded mutual intensityAlankar Kotwal, Anat Levin, Ioannis GkioulekasSIGGRAPH 2020 · 被引用 16 次
- Passive Micron-Scale Time-of-Flight with Sunlight InterferometryAlankar Kotwal, Anat Levin, Ioannis GkioulekasCVPR 2023
- Swept-Angle Synthetic Wavelength InterferometryAlankar Kotwal, Anat Levin, Ioannis GkioulekasCVPR 2023
相关 Paper
- LightDepth: Single-View Depth Self-Supervision from Illumination DeclineJavier Rodriguez Puigvert, Victor M. Batlle, J. M. M. Montiel, Ruben Martinez-Cantin 等ICCV 2023 · 被引用 22 次
- Shape from Thermal Radiation: Passive Ranging Using Multi-spectral LWIR MeasurementsYasuto Nagase, Takahiro Kushida, Kenichiro Tanaka, Takuya Funatomi 等CVPR 2022 · 被引用 12 次
- LightOctree: Lightweight 3D Spatially-Coherent Indoor Lighting EstimationXuecan Wang, Shibang Xiao, Xiaohui LiangCVPR 2024 · 被引用 2 次
- Moving Indoor: Unsupervised Video Depth Learning in Challenging EnvironmentsJunsheng Zhou, Yuwang Wang, Kaihuai Qin, Wenjun ZengICCV 2019 · 被引用 74 次
- Deep 3D Capture: Geometry and Reflectance From Sparse Multi-View ImagesSai Bi, Zexiang Xu, Kalyan Sunkavalli, David J. Kriegman 等CVPR 2020
