Vision without Images: End-to-End Computer Vision from Single Compressive Measurements

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Pan, Fengpu, Gao, Heting, Wen, Jiangtao, Han, Yuxing
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911132515565568
author Pan, Fengpu
Gao, Heting
Wen, Jiangtao
Han, Yuxing
author_facet Pan, Fengpu
Gao, Heting
Wen, Jiangtao
Han, Yuxing
contents Snapshot Compressed Imaging (SCI) offers high-speed, low-bandwidth, and energy-efficient image acquisition, but remains challenged by low-light and low signal-to-noise ratio (SNR) conditions. Moreover, practical hardware constraints in high-resolution sensors limit the use of large frame-sized masks, necessitating smaller, hardware-friendly designs. In this work, we present a novel SCI-based computer vision framework using pseudo-random binary masks of only 8$\times$8 in size for physically feasible implementations. At its core is CompDAE, a Compressive Denoising Autoencoder built on the STFormer architecture, designed to perform downstream tasks--such as edge detection and depth estimation--directly from noisy compressive raw pixel measurements without image reconstruction. CompDAE incorporates a rate-constrained training strategy inspired by BackSlash to promote compact, compressible models. A shared encoder paired with lightweight task-specific decoders enables a unified multi-task platform. Extensive experiments across multiple datasets demonstrate that CompDAE achieves state-of-the-art performance with significantly lower complexity, especially under ultra-low-light conditions where traditional CMOS and SCI pipelines fail.
format Preprint
id arxiv_https___arxiv_org_abs_2501_15122
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Vision without Images: End-to-End Computer Vision from Single Compressive Measurements
Pan, Fengpu
Gao, Heting
Wen, Jiangtao
Han, Yuxing
Computer Vision and Pattern Recognition
Artificial Intelligence
Snapshot Compressed Imaging (SCI) offers high-speed, low-bandwidth, and energy-efficient image acquisition, but remains challenged by low-light and low signal-to-noise ratio (SNR) conditions. Moreover, practical hardware constraints in high-resolution sensors limit the use of large frame-sized masks, necessitating smaller, hardware-friendly designs. In this work, we present a novel SCI-based computer vision framework using pseudo-random binary masks of only 8$\times$8 in size for physically feasible implementations. At its core is CompDAE, a Compressive Denoising Autoencoder built on the STFormer architecture, designed to perform downstream tasks--such as edge detection and depth estimation--directly from noisy compressive raw pixel measurements without image reconstruction. CompDAE incorporates a rate-constrained training strategy inspired by BackSlash to promote compact, compressible models. A shared encoder paired with lightweight task-specific decoders enables a unified multi-task platform. Extensive experiments across multiple datasets demonstrate that CompDAE achieves state-of-the-art performance with significantly lower complexity, especially under ultra-low-light conditions where traditional CMOS and SCI pipelines fail.
title Vision without Images: End-to-End Computer Vision from Single Compressive Measurements
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2501.15122