Pix2HDR -- A pixel-wise acquisition and deep learning-based synthesis approach for high-speed HDR videos

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wang, Caixin, Zhang, Jie, Wilson, Matthew A., Etienne-Cummings, Ralph
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910422356983808
author Wang, Caixin
Zhang, Jie
Wilson, Matthew A.
Etienne-Cummings, Ralph
author_facet Wang, Caixin
Zhang, Jie
Wilson, Matthew A.
Etienne-Cummings, Ralph
contents Accurately capturing dynamic scenes with wide-ranging motion and light intensity is crucial for many vision applications. However, acquiring high-speed high dynamic range (HDR) video is challenging because the camera's frame rate restricts its dynamic range. Existing methods sacrifice speed to acquire multi-exposure frames. Yet, misaligned motion in these frames can still pose complications for HDR fusion algorithms, resulting in artifacts. Instead of frame-based exposures, we sample the videos using individual pixels at varying exposures and phase offsets. Implemented on a monochrome pixel-wise programmable image sensor, our sampling pattern simultaneously captures fast motion at a high dynamic range. We then transform pixel-wise outputs into an HDR video using end-to-end learned weights from deep neural networks, achieving high spatiotemporal resolution with minimized motion blurring. We demonstrate aliasing-free HDR video acquisition at 1000 FPS, resolving fast motion under low-light conditions and against bright backgrounds - both challenging conditions for conventional cameras. By combining the versatility of pixel-wise sampling patterns with the strength of deep neural networks at decoding complex scenes, our method greatly enhances the vision system's adaptability and performance in dynamic conditions.
format Preprint
id arxiv_https___arxiv_org_abs_2310_16139
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Pix2HDR -- A pixel-wise acquisition and deep learning-based synthesis approach for high-speed HDR videos
Wang, Caixin
Zhang, Jie
Wilson, Matthew A.
Etienne-Cummings, Ralph
Image and Video Processing
Computer Vision and Pattern Recognition
Accurately capturing dynamic scenes with wide-ranging motion and light intensity is crucial for many vision applications. However, acquiring high-speed high dynamic range (HDR) video is challenging because the camera's frame rate restricts its dynamic range. Existing methods sacrifice speed to acquire multi-exposure frames. Yet, misaligned motion in these frames can still pose complications for HDR fusion algorithms, resulting in artifacts. Instead of frame-based exposures, we sample the videos using individual pixels at varying exposures and phase offsets. Implemented on a monochrome pixel-wise programmable image sensor, our sampling pattern simultaneously captures fast motion at a high dynamic range. We then transform pixel-wise outputs into an HDR video using end-to-end learned weights from deep neural networks, achieving high spatiotemporal resolution with minimized motion blurring. We demonstrate aliasing-free HDR video acquisition at 1000 FPS, resolving fast motion under low-light conditions and against bright backgrounds - both challenging conditions for conventional cameras. By combining the versatility of pixel-wise sampling patterns with the strength of deep neural networks at decoding complex scenes, our method greatly enhances the vision system's adaptability and performance in dynamic conditions.
title Pix2HDR -- A pixel-wise acquisition and deep learning-based synthesis approach for high-speed HDR videos
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2310.16139