Data Generation Scheme for Thermal Modality with Edge-Guided Adversarial Conditional Diffusion Model

TL;DR

This paper introduces an edge-guided conditional diffusion model that generates high-quality pseudo thermal images from visible images, improving thermal vision data augmentation especially in challenging conditions.

Contribution

The novel edge-guided conditional diffusion framework effectively aligns pseudo thermal images with visible image edges, enhancing thermal data generation for deep learning applications.

Findings

ECDM outperforms existing methods in image quality

The two-stage adversarial training filters visible-specific edges

Generated images improve thermal object detection performance

Abstract

In challenging low light and adverse weather conditions,thermal vision algorithms,especially object detection,have exhibited remarkable potential,contrasting with the frequent struggles encountered by visible vision algorithms. Nevertheless,the efficacy of thermal vision algorithms driven by deep learning models remains constrained by the paucity of available training data samples. To this end,this paper introduces a novel approach termed the edge guided conditional diffusion model. This framework aims to produce meticulously aligned pseudo thermal images at the pixel level,leveraging edge information extracted from visible images. By utilizing edges as contextual cues from the visible domain,the diffusion model achieves meticulous control over the delineation of objects within the generated images. To alleviate the impacts of those visible-specific edge information that should not appear in the thermal domain,a two-stage modality adversarial training strategy is proposed to filter them out from the generated images by differentiating the visible and thermal modality. Extensive experiments on LLVIP demonstrate ECDM s superiority over existing state-of-the-art approaches in terms of image generation quality.