BeyondFusion: Self-Aligned Latent Diffusion for Calibration-Free Infrared Super-Resolution and Infrared-Visible Fusion

• URL: http://arxiv.org/abs/2607.24110v1
• Date: Mon, 27 Jul 2026 07:48:02 GMT
• Title: BeyondFusion: Self-Aligned Latent Diffusion for Calibration-Free Infrared Super-Resolution and Infrared-Visible Fusion
• Abstract summary: BeyondFusion is a framework for calibration-free visible-guided infrared super-resolution and infrared-visible fusion tasks.<n>The proposed framework supports both task-specific training and joint training where two tasks are optimized and executed as two readouts of the same generative process.<n> experiments on public benchmarks and a mobile infrared-visible imaging system show strong performance across aligned inputs, low-resolution infrared observations, synthetic misalignments, and real mobile captures with unsynchronized sensors.
• Score: 33.54822144332431
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Mobile infrared-visible imaging typically pairs a compact infrared sensor with a high-resolution visible camera for complementary perception. While cross-sensor misalignment caused by different optics, viewpoints, fields of view, and exposure timings hinders practical deployment. In this paper, we propose BeyondFusion, a unified latent diffusion framework for calibration-free visible-guided infrared super-resolution and infrared-visible fusion tasks. The proposed framework supports both task-specific training and joint training where two tasks are optimized and executed as two readouts of the same generative process. Instead of relying on explicit registration or geometric warping, BeyondFusion introduces a cross-modal self-aligning (CMSA) module into the denoising U-Net. CMSA reorganizes infrared and visible latent tokens into a shared attention space to learn content-adaptive cross-modal correspondence during the denoising process. Together with misalignment augmentation module, the model is facilitated to exploit visible structural and semantic cues while preserving thermal consistency, enabling high-frequency infrared reconstruction and informative fused-image generation under uncalibrated conditions. Extensive experiments on public benchmarks and a mobile infrared-visible imaging system show strong performance across aligned inputs, low-resolution infrared observations, synthetic misalignments, and real mobile captures with unsynchronized sensors. Ablation studies, unified training analysis, and downstream pedestrian detection further validate the effectiveness of BeyondFusion for calibration-free multimodal imaging.

Related papers

• FSCM: Frequency-Enhanced Spatial-Spectral Coupled Mamba for Infrared Hyperspectral Image Colorization [10.509841173943387]
  This paper presents a spectral-information-guided GAN framework for infrared colorization.<n>Within FSCM, a frequency-enhanced spatial-spectral state-space generator composed of cascaded FSB units is constructed.<n>Experiments show that FSCM outperforms existing infrared colorization methods in visual quality and semantic fidelity.
  arXiv  Detail & Related papers  (2026-05-13T15:48:58Z)
• Perceptual Region-Driven Infrared-Visible Co-Fusion for Extreme Scene Enhancement [8.10747908396949]
  We propose a region perception-based fusion framework that combines multi-exposure and multi-modal imaging.<n>This framework co-fuses multi-modal and multi-exposure data, overcoming single-exposure method limitations in extreme environments.<n> Experiments conducted on both synthetic and real-world data demonstrate superior image clarity and improved performance compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-12-06T11:17:35Z)
• DifIISR: A Diffusion Model with Gradient Guidance for Infrared Image Super-Resolution [32.53713932204663]
  DifIISR is an infrared image super-resolution diffusion model optimized for visual quality and perceptual performance.<n>We introduce an infrared thermal spectrum distribution regulation to preserve visual fidelity.<n>We incorporate various visual foundational models as the perceptual guidance for downstream visual tasks.
  arXiv  Detail & Related papers  (2025-03-03T05:20:57Z)
• Bringing RGB and IR Together: Hierarchical Multi-Modal Enhancement for Robust Transmission Line Detection [67.02804741856512]
  We propose a novel Hierarchical Multi-Modal Enhancement Network (HMMEN) that integrates RGB and IR data for robust and accurate TL detection.<n>Our method introduces two key components: (1) a Mutual Multi-Modal Enhanced Block (MMEB), which fuses and enhances hierarchical RGB and IR feature maps in a coarse-to-fine manner, and (2) a Feature Alignment Block (FAB) that corrects misalignments between decoder outputs and IR feature maps by leveraging deformable convolutions.
  arXiv  Detail & Related papers  (2025-01-25T06:21:06Z)
• Contourlet Refinement Gate Framework for Thermal Spectrum Distribution Regularized Infrared Image Super-Resolution [54.293362972473595]
  Image super-resolution (SR) aims to reconstruct high-resolution (HR) images from their low-resolution (LR) counterparts. Current approaches to address SR tasks are either dedicated to extracting RGB image features or assuming similar degradation patterns. We propose a Contourlet refinement gate framework to restore infrared modal-specific features while preserving spectral distribution fidelity.
  arXiv  Detail & Related papers  (2024-11-19T14:24:03Z)
• Infrared-Assisted Single-Stage Framework for Joint Restoration and Fusion of Visible and Infrared Images under Hazy Conditions [9.415977819944246]
  We propose a joint learning framework that utilizes infrared image for the restoration and fusion of hazy IR-VIS images.<n>Our method effectively fuses IR-VIS images while removing haze, yielding clear, haze-free fusion results.
  arXiv  Detail & Related papers  (2024-11-16T02:57:12Z)
• Frequency Domain Modality-invariant Feature Learning for Visible-infrared Person Re-Identification [79.9402521412239]
  We propose a novel Frequency Domain modality-invariant feature learning framework (FDMNet) to reduce modality discrepancy from the frequency domain perspective. Our framework introduces two novel modules, namely the Instance-Adaptive Amplitude Filter (IAF) and the Phrase-Preserving Normalization (PPNorm)
  arXiv  Detail & Related papers  (2024-01-03T17:11:27Z)
• Breaking Modality Disparity: Harmonized Representation for Infrared and Visible Image Registration [66.33746403815283]
  We propose a scene-adaptive infrared and visible image registration. We employ homography to simulate the deformation between different planes. We propose the first ground truth available misaligned infrared and visible image dataset.
  arXiv  Detail & Related papers  (2023-04-12T06:49:56Z)
• Unsupervised Misaligned Infrared and Visible Image Fusion via Cross-Modality Image Generation and Registration [59.02821429555375]
  We present a robust cross-modality generation-registration paradigm for unsupervised misaligned infrared and visible image fusion. To better fuse the registered infrared images and visible images, we present a feature Interaction Fusion Module (IFM)
  arXiv  Detail & Related papers  (2022-05-24T07:51:57Z)
• Target-aware Dual Adversarial Learning and a Multi-scenario Multi-Modality Benchmark to Fuse Infrared and Visible for Object Detection [65.30079184700755]
  This study addresses the issue of fusing infrared and visible images that appear differently for object detection. Previous approaches discover commons underlying the two modalities and fuse upon the common space either by iterative optimization or deep networks. This paper proposes a bilevel optimization formulation for the joint problem of fusion and detection, and then unrolls to a target-aware Dual Adversarial Learning (TarDAL) network for fusion and a commonly used detection network.
  arXiv  Detail & Related papers  (2022-03-30T11:44:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.