DRPFNet: Dual-domain Residual Progressive Fusion Network for RGB-Thermal Object Detection

2026-08-04

AI Summary

This work addresses key limitations in existing RGB-thermal object detection methods—namely, fragmented cross-level knowledge transfer, insufficient noise suppression, and the lack of coordination between frequency and spatial domains during multi-scale fusion. To overcome these issues, we propose a dual-domain residual progressive fusion mechanism that jointly optimizes structure, features, and enhancement across three levels. This enables bidirectional cross-scale knowledge propagation, frequency-band-guided joint frequency-spatial representation, and edge-aware fine-grained foreground-background discrimination. Extensive experiments on two public RGB-T datasets demonstrate that our method significantly improves detection accuracy and robustness under challenging lighting and weather conditions, thereby validating the effectiveness of our hierarchical collaborative fusion strategy.

Abstract

RGB-thermal (RGB-T) object detection aims to fuse complementary information from visible and thermal modalities to achieve robust detection under varying illumination and weather conditions. Current methods typically employ attention mechanisms or transformers to perform cross-modal fusion independently at each feature scale, directly combining RGB and thermal features in the spatial domain. However, they still face significant limitations: cross-level knowledge inheritance caused by independent fusion at each scale,suppressing noise continuously due to the lack of bidirectional optimization, and information degradation induced by the absence of frequency-spatial collaboration. To address these issues, we propose DRPFNet, a Dual-domain Residual Progressive Fusion Network that constructs a unified information flow optimization system from three synergistic levels:structure, feature, and enhancement. At the structural level, we establish cross-scale propagation through bottom-up knowledge accumulation and bidirectional enhancement,ensuring smooth information flow. At the feature level, we collaboratively extract RGB high-frequency edges and thermal low-frequency structures via frequency band separation and edge guidance, guaranteeing representation quality. At the enhancement level, we enhance foreground-background discrimination through edge-guided dual-domain refinement,achieving precise object localization.Extensive experiments on two public RGB-T datasets demonstrate that our method achieves competitive performance with competitive efficiency, validating the effectiveness of this hierarchical collaborative strategy.

Problem

• RGB-thermal object detection
• cross-modal fusion
• multi-scale feature integration
• frequency-spatial collaboration
• information degradation

Innovation

• dual-domain fusion
• cross-scale propagation
• frequency-spatial collaboration
• edge-guided refinement
• RGB-thermal object detection