DeepAI AI Chat
Log In Sign Up

Dif-Fusion: Towards High Color Fidelity in Infrared and Visible Image Fusion with Diffusion Models

by   Jun Yue, et al.
Peking University

Color plays an important role in human visual perception, reflecting the spectrum of objects. However, the existing infrared and visible image fusion methods rarely explore how to handle multi-spectral/channel data directly and achieve high color fidelity. This paper addresses the above issue by proposing a novel method with diffusion models, termed as Dif-Fusion, to generate the distribution of the multi-channel input data, which increases the ability of multi-source information aggregation and the fidelity of colors. In specific, instead of converting multi-channel images into single-channel data in existing fusion methods, we create the multi-channel data distribution with a denoising network in a latent space with forward and reverse diffusion process. Then, we use the the denoising network to extract the multi-channel diffusion features with both visible and infrared information. Finally, we feed the multi-channel diffusion features to the multi-channel fusion module to directly generate the three-channel fused image. To retain the texture and intensity information, we propose multi-channel gradient loss and intensity loss. Along with the current evaluation metrics for measuring texture and intensity fidelity, we introduce a new evaluation metric to quantify color fidelity. Extensive experiments indicate that our method is more effective than other state-of-the-art image fusion methods, especially in color fidelity.


page 1

page 4

page 5

page 7

page 8

page 9

page 10

page 13


NestFuse: An Infrared and Visible Image Fusion Architecture based on Nest Connection and Spatial/Channel Attention Models

In this paper we propose a novel method for infrared and visible image f...

DDFM: Denoising Diffusion Model for Multi-Modality Image Fusion

Multi-modality image fusion aims to combine different modalities to prod...

Infrared and Visible Image Fusion via Interactive Compensatory Attention Adversarial Learning

The existing generative adversarial fusion methods generally concatenate...

Bayesian Fusion for Infrared and Visible Images

Infrared and visible image fusion has been a hot issue in image fusion. ...

Joint Intensity-Gradient Guided Generative Modeling for Colorization

This paper proposes an iterative generative model for solving the automa...

A Cross-Modal Image Fusion Theory Guided by Human Visual Characteristics

The characteristics of feature selection, nonlinear combination and mult...

A Joint Convolution Auto-encoder Network for Infrared and Visible Image Fusion

Background: Leaning redundant and complementary relationships is a criti...