Audio-Infused Automatic Image Colorization by Exploiting Audio Scene Semantics

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhao, Pengcheng, Chen, Yanxiang, Zhao, Yang, Zhang, Zhao
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910750164910080
author Zhao, Pengcheng
Chen, Yanxiang
Zhao, Yang
Zhang, Zhao
author_facet Zhao, Pengcheng
Chen, Yanxiang
Zhao, Yang
Zhang, Zhao
contents Automatic image colorization is inherently an ill-posed problem with uncertainty, which requires an accurate semantic understanding of scenes to estimate reasonable colors for grayscale images. Although recent interaction-based methods have achieved impressive performance, it is still a very difficult task to infer realistic and accurate colors for automatic colorization. To reduce the difficulty of semantic understanding of grayscale scenes, this paper tries to utilize corresponding audio, which naturally contains extra semantic information about the same scene. Specifically, a novel and pluggable audio-infused automatic image colorization (AIAIC) method is proposed, which consists of three stages. First, we take color image semantics as a bridge and pretrain a colorization network guided by color image semantics. Second, the natural co-occurrence of audio and video is utilized to learn the color semantic correlations between audio and visual scenes. Third, the implicit audio semantic representation is fed into the pretrained network to finally realize the audio-guided colorization. The whole process is trained in a self-supervised manner without human annotation. Experiments demonstrate that audio guidance can effectively improve the performance of automatic colorization, especially for some scenes that are difficult to understand only from visual modality.
format Preprint
id arxiv_https___arxiv_org_abs_2401_13270
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Audio-Infused Automatic Image Colorization by Exploiting Audio Scene Semantics
Zhao, Pengcheng
Chen, Yanxiang
Zhao, Yang
Zhang, Zhao
Computer Vision and Pattern Recognition
Artificial Intelligence
Automatic image colorization is inherently an ill-posed problem with uncertainty, which requires an accurate semantic understanding of scenes to estimate reasonable colors for grayscale images. Although recent interaction-based methods have achieved impressive performance, it is still a very difficult task to infer realistic and accurate colors for automatic colorization. To reduce the difficulty of semantic understanding of grayscale scenes, this paper tries to utilize corresponding audio, which naturally contains extra semantic information about the same scene. Specifically, a novel and pluggable audio-infused automatic image colorization (AIAIC) method is proposed, which consists of three stages. First, we take color image semantics as a bridge and pretrain a colorization network guided by color image semantics. Second, the natural co-occurrence of audio and video is utilized to learn the color semantic correlations between audio and visual scenes. Third, the implicit audio semantic representation is fed into the pretrained network to finally realize the audio-guided colorization. The whole process is trained in a self-supervised manner without human annotation. Experiments demonstrate that audio guidance can effectively improve the performance of automatic colorization, especially for some scenes that are difficult to understand only from visual modality.
title Audio-Infused Automatic Image Colorization by Exploiting Audio Scene Semantics
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2401.13270