← 研踪 PaperTrailCVF · CVPR 2026:cvf:e5ae0b7e71c3957805d74a9dd831f072 · 记录 #1
Lumosaic: Hyperspectral Video via Active Illumination and Coded-Exposure Pixels
Verma, DhruvQiu, AndrewRangel, RobertoBarman, AyandevYang, HaoHu, ChenjiaZhang, FengqiGenov, RomanLindell, David B.Kutulakos, Kiriakos N.Mariakakis, Alex 来源日期(仅到年份) 2026
来源记录日期 2026
雷达观测 2026-11-05 03:41
摘要
We present Lumosaic, a compact active hyperspectral video system designed for real-time capture of dynamic scenes. Our approach combines a programmable narrowband LED array with a coded-exposure-pixel (CEP) camera capable of high-speed pixel-wise exposure, thereby enabling joint encoding of scene information across space, time, and wavelength within each video frame. Unlike passive snapshot systems that divide light across multiple spectral channels simultaneously and assume no motion during a frame's exposure, Lumosaic actively synchronizes illumination and sub-frame exposures to improve photon utilization and preserve spectral fidelity under motion. A learning-based reconstruction pipeline then recovers 31-channel hyperspectral (400-700 nm) video at 30 fps and VGA resolution, producing temporally coherent and spectrally accurate reconstructions. Experiments on synthetic benchmarks and real-world dynamic scenes demonstrate that Lumosaic significantly improves reconstruction fidelity and temporal stability over existing snapshot hyperspectral imaging systems, enabling robust hyperspectral video across diverse materials and motion conditions.
论文发现出处
这些页面提供论文线索,不代表同行评审或质量认证。
观测到的版本
平台记录号代表本站观测到的元数据变化,不是作者修订号。来源日期仅到月份或年份时,按该月或该年首日存档。
记录 #1 · 2026 · 最新观测版本
Lumosaic: Hyperspectral Video via Active Illumination and Coded-Exposure Pixels
We present Lumosaic, a compact active hyperspectral video system designed for real-time capture of dynamic scenes. Our approach combines a programmable narrowband LED array with a coded-exposure-pixel (CEP) camera capable of high-speed pixel-wise exposure, thereby enabling joint encoding of scene information across space, time, and wavelength within each video frame. Unlike passive snapshot systems that divide light across multiple spectral channels simultaneously and assume no motion during a frame's exposure, Lumosaic actively synchronizes illumination and sub-frame exposures to improve photon utilization and preserve spectral fidelity under motion. A learning-based reconstruction pipeline then recovers 31-channel hyperspectral (400-700 nm) video at 30 fps and VGA resolution, producing temporally coherent and spectrally accurate reconstructions. Experiments on synthetic benchmarks and real-world dynamic scenes demonstrate that Lumosaic significantly improves reconstruction fidelity and temporal stability over existing snapshot hyperspectral imaging systems, enabling robust hyperspectral video across diverse materials and motion conditions.
查看此版本解读 →查看此版本原文 ↗