English

Frequency-Guided Fusion For RGB-Thermal Semantic Segmentation

Computer Vision and Pattern Recognition 2026-05-27 v1

Abstract

Semantic segmentation in complex environments such as urban driving scenes remains challenging under adverse lighting conditions, where RGB images alone provide insufficient information. RGB-Thermal fusion leverages the complementary strengths of visible and infrared imagery to improve scene understanding; however, effectively integrating these heterogeneous modalities at varying levels of feature abstraction remains an open problem. In this paper, we propose a multi-modal fusion architecture built upon dual ConvNeXt V2 backbones that employs stage-wise, modality-adaptive fusion strategies. For early-stage features, we introduce a Frequency-Based Fusion Module that decomposes infrared features into low- and high-frequency components via Gaussian filtering, applies dual-branch spatial attention to selectively emphasize thermal patterns and fine-grained boundaries, and integrates them with RGB features through a confidence-gated residual mechanism. For late-stage features, we design a semantic fusion module with cross-modal attention and multi-scale depthwise convolutions to capture semantic correspondences across modalities. The fused features are decoded via a PANet-style bidirectional decoder with deep supervision. Experiments on MFNet and PST900 demonstrate that our lightest variant achieves 61.73\% and 86.24\% mIoU, respectively, with only 35.43M parameters, outperforming recent methods while using substantially fewer parameters and lower computational cost. Code is available at https://github.com/ismailemrecntz/VISIBLE-INFRARED-SENSOR-FUSION

Keywords

Cite

@article{arxiv.2605.26273,
  title  = {Frequency-Guided Fusion For RGB-Thermal Semantic Segmentation},
  author = {İsmail Emre Canıtez and Özgür Erkent},
  journal= {arXiv preprint arXiv:2605.26273},
  year   = {2026}
}

Comments

9 pages, 7 figures, To be Presented at Perception Beyond the Visible Spectrum workshop series (IEEE PBVS) at CVPR, 2026

R2 v1 2026-07-22T07:33:17.411Z