Saved in:
Bibliographic Details
Main Author: Wu, Tong
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.12551
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908882774786048
author Wu, Tong
author_facet Wu, Tong
contents We propose PISE, a physics-informed deep ghost imaging framework for low-bandwidth edge perception. By combining adjoint operator initialization with semantic guidance, PISE improves classification accuracy by 2.57% and reduces variance by 9x at 5% sampling.
format Preprint
id arxiv_https___arxiv_org_abs_2601_12551
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle PISE: Physics-Anchored Semantically-Enhanced Deep Computational Ghost Imaging for Robust Low-Bandwidth Machine Perception
Wu, Tong
Computer Vision and Pattern Recognition
Image and Video Processing
We propose PISE, a physics-informed deep ghost imaging framework for low-bandwidth edge perception. By combining adjoint operator initialization with semantic guidance, PISE improves classification accuracy by 2.57% and reduces variance by 9x at 5% sampling.
title PISE: Physics-Anchored Semantically-Enhanced Deep Computational Ghost Imaging for Robust Low-Bandwidth Machine Perception
topic Computer Vision and Pattern Recognition
Image and Video Processing
url https://arxiv.org/abs/2601.12551