Saved in:
Bibliographic Details
Main Authors: Li, Shen, Jiang, Lei, Wang, Wei, Hu, Hongwei, Li, Liang
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2411.13021
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910705654956032
author Li, Shen
Jiang, Lei
Wang, Wei
Hu, Hongwei
Li, Liang
author_facet Li, Shen
Jiang, Lei
Wang, Wei
Hu, Hongwei
Li, Liang
contents This paper shows a proof-of-concept that, given a typical 3-channel images but in a randomly permuted channel order, a model (termed as Chanel-Orderer) with ad-hoc inductive biases in terms of both architecture and loss functions can accurately predict the channel ordering and knows how to make it right. Specifically, Chanel-Orderer learns to score each of the three channels with the priors of object semantics and uses the resulting scores to predict the channel ordering. This brings up benefits into a typical scenario where an \texttt{RGB} image is often mis-displayed in the \texttt{BGR} format and needs to be corrected into the right order. Furthermore, as a byproduct, the resulting model Chanel-Orderer is able to tell whether a given image is a near-gray-scale image (near-monochromatic) or not (polychromatic). Our research suggests that Chanel-Orderer mimics human visual coloring of our physical natural world.
format Preprint
id arxiv_https___arxiv_org_abs_2411_13021
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Chanel-Orderer: A Channel-Ordering Predictor for Tri-Channel Natural Images
Li, Shen
Jiang, Lei
Wang, Wei
Hu, Hongwei
Li, Liang
Computer Vision and Pattern Recognition
This paper shows a proof-of-concept that, given a typical 3-channel images but in a randomly permuted channel order, a model (termed as Chanel-Orderer) with ad-hoc inductive biases in terms of both architecture and loss functions can accurately predict the channel ordering and knows how to make it right. Specifically, Chanel-Orderer learns to score each of the three channels with the priors of object semantics and uses the resulting scores to predict the channel ordering. This brings up benefits into a typical scenario where an \texttt{RGB} image is often mis-displayed in the \texttt{BGR} format and needs to be corrected into the right order. Furthermore, as a byproduct, the resulting model Chanel-Orderer is able to tell whether a given image is a near-gray-scale image (near-monochromatic) or not (polychromatic). Our research suggests that Chanel-Orderer mimics human visual coloring of our physical natural world.
title Chanel-Orderer: A Channel-Ordering Predictor for Tri-Channel Natural Images
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.13021