Proceedings ArticleDOI
Random coded sampling for high-speed HDR video
Travis Portz,Li Zhang,Hongrui Jiang +2 more
- pp 1-8
TLDR
This work proposes a novel method for capturing high-speed, high dynamic range video with a single low-speed camera using a coded sampling technique that can maintain a 100% light throughput similarly to existing cameras and can be implemented on a single chip, making it suitable for small form factors.Abstract:
We propose a novel method for capturing high-speed, high dynamic range video with a single low-speed camera using a coded sampling technique. Traditional video cameras use a constant full-frame exposure time, which makes temporal super-resolution difficult due to the ill-posed nature of inverting the sampling operation. Our method samples at the same rate as the traditional low-speed camera but uses random per-pixel exposure times and offsets. By exploiting temporal and spatial redundancy in the video, we can reconstruct a high-speed video from the coded input. Furthermore, the different exposure times used in our sampling scheme enable us to obtain a higher dynamic range than a traditional camera or other temporal superresolution methods. We validate our approach using simulation and provide a detailed discussion on how to make a hardware implementation. In particular, we believe that our approach can maintain a 100% light throughput similarly to existing cameras and can be implemented on a single chip, making it suitable for small form factors.read more
Citations
More filters
Journal ArticleDOI
Snapshot Compressive Imaging: Principle, Implementation, Theory, Algorithms and Applications.
TL;DR: In this article, a review of recent advances in Snapshot compressive imaging hardware, theory and algorithms, including both optimization-based and deep learning-based algorithms, is presented.
Journal ArticleDOI
Snapshot Compressive Imaging: Theory, Algorithms, and Applications
TL;DR: In this paper, the authors review recent advances in Snapshot Compressive Imaging (SCI) hardware, theory, and algorithms, including both optimization-based and deep learning-based algorithms.
Journal ArticleDOI
Convolutional Sparse Coding for High Dynamic Range Imaging
TL;DR: In this article, a convolutional sparse coding (CSC) based method is proposed to recover high-quality HDRI images from a single coded exposure, which achieves higher quality reconstructions than alternative methods.
Journal ArticleDOI
High spatio-temporal resolution video with compressed sensing.
Roman Koller,Lukas Schmid,Nathan Matsuda,Thomas Niederberger,Leonidas Spinoulas,Oliver Cossairt,Guido M. Schuster,Aggelos K. Katsaggelos +7 more
TL;DR: A prototype compressive video camera is presented that encodes scene movement using a translated binary photomask in the optical path, and the use of a printed binary mask allows reconstruction at higher spatial resolutions than has been previously demonstrated.
Journal ArticleDOI
Neural Sensors: Learning Pixel Exposures for HDR Imaging and Video Compressive Sensing With Programmable Sensors
TL;DR: This work introduces neural sensors as a methodology to optimize per-pixel shutter functions jointly with a differentiable image processing method, such as a neural network, in an end-to-end fashion and demonstrates how to leverage emerging programmable and re-configurable sensor–processors to implement the optimized exposure functions directly on the sensor.
References
More filters
Book
Distributed Optimization and Statistical Learning Via the Alternating Direction Method of Multipliers
TL;DR: It is argued that the alternating direction method of multipliers is well suited to distributed convex optimization, and in particular to large-scale problems arising in statistics, machine learning, and related areas.
Book ChapterDOI
A duality based approach for realtime TV-L 1 optical flow
TL;DR: This work presents a novel approach to solve the TV-L1 formulation, which is based on a dual formulation of the TV energy and employs an efficient point-wise thresholding step.
Journal ArticleDOI
Video enhancement using per-pixel virtual exposures
Eric P. Bennett,Leonard McMillan +1 more
TL;DR: This work enhances underexposed, low dynamic range videos by adaptively and independently varying the exposure at each photoreceptor in a post-process, which is a dynamic function of both the spatial neighborhood and temporal history at each pixel.
Proceedings ArticleDOI
Video from a single coded exposure photograph using a learned over-complete dictionary
TL;DR: It is shown that the proposed techniques for sampling, representing and reconstructing the space-time volume can effectively reconstruct a video from a single image maintaining high spatial resolution.
Proceedings ArticleDOI
P2C2: Programmable pixel compressive camera for high speed imaging
TL;DR: By modeling such spatio-temporal redundancies in a video volume, one can faithfully recover the underlying high-speed video frames from the observed low speed coded video by proposing a reconstruction algorithm that uses the data from P2C2 along with additional priors about videos to perform temporal super-resolution.