Skip to content
Preprint

SGPDFuse: Semantically-Guided Physics-Disentanglement General Multi-Modal Image Fusion

Aug 2026 · 0 citations · 41 references
Computer Science

TL;DR

SGPDFuse is proposed, which bridges this gap by mapping inputs into a physics-disentangled structural representation via a Semantic-Physical Parametric Bridge (SPPB) built on pretrained vision foundation models, utilizing the Intrinsic-Variation principle to decouple invariant scene attributes from transient environmental factors.

Abstract

Multimodal image fusion (MMIF) aims to integrate complementary sensor data into a single representation that preserves intrinsic scene reality while eliminating environmental interferences. Most existing approaches rely on blind feature aggregation, which excels at signal accumulation but fails to distinguish essential content from physical degradations. We propose SGPDFuse, which bridges this gap by mapping inputs into a physics-disentangled structural representation via a Semantic-Physical Parametric Bridge (SPPB) built on pretrained vision foundation models, utilizing the Intrinsic-Variation principle to decouple invariant scene attributes from transient environmental factors. To guide this decomposition, we introduce a Semantic Alignment mechanism: we explicitly anchor the fused representation to salient semantic features in the same foundation model feature space via cosine similarity to preserve critical targets, while enforcing physical texture fidelity through Gram-matrix regularization to strictly eliminate unnatural artifacts. Extensive experiments demonstrate that SGPDFuse achieves state-of-the-art performance across infrared-visible, multi-focus, and multi-exposure benchmarks using a single architecture.

View source

Similar papers

Preprint Aug 2026

P2Fusion: Prompt-based Progressive Infrared-Visible Image Fusion via Dual-Prior Distillation

P2Fusion, a prior-guided distillation-based framework that reformulates IVIF via dual intrinsic prompts, distill image-intrinsic priors, thermal saliency and spatial quality, into learnable dynamic regulators, and enables the network to adaptively mediate modal competition through expert specialization.

Yi Shi, Huichao Xie, Yu-Qing Wang et al. · 0 citations
Conference Open access Sep 2026

G-SalAlignMamba: Geometry-Aware Vision Mamba for Dual-Modal Salient Object Detection

G-SalAlignMamba is proposed, a geometry-aware framework tailored for dual-modal SOD that introduces Geometry-Aware Encoding with explicit alignment to correct spatial shifts, Semantics-Informed Refinement to prevent signal dilution by prioritizing foregrounds, and Structure-Preserving Decoding that integrates explicit...

Hai-Xiao Gao, Yi-Min Zheng, Meng-Ke Song et al. · 0 citations
#machine learning Preprint Aug 2026

BenthicDINO: Physics-Informed Self-Distillation for View-Invariant Side-Scan Sonar Representations

A physics-informed self-distillation framework built upon the DINOv3 architecture utilizing a ConvNeXt-v2-Tiny backbone to maximize data efficiency and enforces view-invariance, and proposes a dense, hierarchical feature fusion strategy across all four network stages to preserve fine-grained sediment details alongside...

Taqi Hamoda, Hayat Rajani, Nuno Gracias · 0 citations
Preprint Aug 2026

PoseAdapter: Dual-Stream 2.5D Controllable Image Generation for Complex Multi-Object Scenes

PoseAdapter, a lightweight framework for high-fidelity 2.5D controllable image generation, and a Context-Aware Dual-Stream Representation, to resolve the generative trade-off between strict instance isolation and global coherence.

Yu-Feng Chi, Hui-Min Ma, Fan Gao et al. · 0 citations
Preprint Sep 2026

M3GD: Multi-Modal Multi-View Geometric Diffusion for Camera--LiDAR Novel View Synthesis

M3GD is presented, a Camera--LiDAR multimodal representation for generative NVS that composes independently pretrained 2D image and 3D point-cloud foundation models without separately pretraining a cross-modal translator.

Yang Zhou, Jiuhong Xiao, Shi-Zhao Ye et al. · 0 citations
Preprint Sep 2026

Bridging Modalities and Tasks: A Unified Hierarchical ViT for SAR-to-Optical Translation and Semantic Segmentation

A unified collaborative dual-task learning framework that jointly optimizes S2O image translation and semantic segmentation through a shared hierarchical Vision Transformer is proposed, which achieves competitive S2O translation quality and semantic segmentation performance.

Si-Yuan Liu, Xu-Ze Zhang, Yong-Shun Wang et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.