paper-with-me

홈 › Papers

A Dual Sensor Computational Camera for High Quality Dark Videography

2022-04-11 · Yuxiao Cheng, Runzhao Yang, Zhihong Zhang, Jinli Suo, Qionghai Dai

Videos captured under low light conditions suffer from severe noise. A variety of efforts have been devoted to image/video noise suppression and made large progress. However, in extremely dark scenarios, extensive photon starvation would hamper precise noise modeling. Instead, developing an imaging system collecting more photons is a more effective way for high-quality video capture under low illuminations. In this paper, we propose to build a dual-sensor camera to additionally collect the photons in NIR wavelength, and make use of the correlation between RGB and near-infrared (NIR) spectrum to perform high-quality reconstruction from noisy dark video pairs. In hardware, we build a compact dual-sensor camera capturing RGB and NIR videos simultaneously. Computationally, we propose a dual-channel multi-frame attention network (DCMAN) utilizing spatial-temporal-spectral priors to reconstruct the low-light RGB and NIR videos. In addition, we build a high-quality paired RGB and NIR video dataset, based on which the approach can be applied to different sensors easily by training the DCMAN model with simulated noisy input following a physical-process-based CMOS noise model. Both experiments on synthetic and real videos validate the performance of this compact dual-sensor camera design and the corresponding reconstruction algorithm in dark videography.

📄 PDF Abstract BibTeX arXiv:2204.04987

Code (0)

등록된 구현이 없습니다.

Tasks

Vocal Bursts Intensity Prediction

Similar Papers 제목 키워드 기반

FloatingFusion: Depth from ToF and Image-stabilized Stereo Cameras

2022-10-06 · Andreas Meuleman, Hakyeong Kim, James Tompkin, Min H. Kim

High-accuracy per-pixel depth is vital for computational photography, so smartphones now have multimodal camera systems with time-of-flight (ToF) depth sensors and multiple color cameras. However, producing accurate high…

Du$^2$Net: Learning Depth Estimation from Dual-Cameras and Dual-Pixels

2020-03-31 · Yinda Zhang, Neal Wadhwa, Sergio Orts-Escolano, Christian Häne 외

Computational stereo has reached a high level of accuracy, but degrades in the presence of occlusions, repeated textures, and correspondence errors along edges. We present a novel approach based on neural networks for de…

Depth EstimationStereo Matching

Du²Net: Learning Depth Estimation from Dual-Cameras and Dual-Pixels

2020-08-01 · ECCV 2020 8 · Yinda Zhang, Neal Wadhwa, Sergio Orts-Escolano, Christian Häne 외

Computational stereo has reached a high level of accuracy, but degrades in the presence of occlusions, repeated textures, and correspondence errors along edges. We present a novel approach based on neural networks for de…

Depth EstimationStereo Matching

A Deep Learning-based Radar and Camera Sensor Fusion Architecture for Object Detection

2020-05-15 · 2019 Sensor Data Fusion: Trends, Solutions, Applications (SDF) 2019 10 · Felix Nobis, Maximilian Geisslinger, Markus Weber, Johannes Betz 외

Object detection in camera images, using deep learning has been proven successfully in recent years. Rising detection rates and computationally efficient network structures are pushing this technique towards application …

2D Object Detectionobject-detectionObject DetectionSensor Fusion

Dual-Camera Joint Deblurring-Denoising

2023-09-16 · Shayan shekarforoush, Amanpreet Walia, Marcus A. Brubaker, Konstantinos G. Derpanis 외

Recent image enhancement methods have shown the advantages of using a pair of long and short-exposure images for low-light photography. These image modalities offer complementary strengths and weaknesses. The former yiel…

DeblurringDenoisingImage Enhancement