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

arXiv: https://arxiv.org/abs/2608.29220 · HTML: https://mlsanity.com/paper/2608.29220/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 41 references that are in the map.
- First posted on arXiv 29 Aug 2026.

## Builds on (most cited first, 19 of 19)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Understanding disentangling in β-VAE](https://mlsanity.com/paper/1804.03599/) (2018)
- [Target-aware Dual Adversarial Learning and a Multi-scenario Multi-Modality Benchmark to Fuse Infrared and Visible for Object Detection](https://mlsanity.com/paper/2203.16220/) (2022)
- [CDDFuse: Correlation-Driven Dual-Branch Feature Decomposition for Multi-Modality Image Fusion](https://mlsanity.com/paper/2211.14461/) (2022)
- [DenseFuse: A Fusion Approach to Infrared and Visible Images](https://mlsanity.com/paper/1804.08361/) (2018)
- [DDFM: Denoising Diffusion Model for Multi-Modality Image Fusion](https://mlsanity.com/paper/2303.06840/) (2023)
- [Multi-interactive Feature Learning and a Full-time Multi-modality Benchmark for Image Fusion and Segmentation](https://mlsanity.com/paper/2308.02097/) (2023)
- [RFN-Nest: An end-to-end residual fusion network for infrared and visible images](https://mlsanity.com/paper/2103.04286/) (2021)
- [Text-IF: Leveraging Semantic Text Guidance for Degradation-Aware and Interactive Image Fusion](https://mlsanity.com/paper/2403.16387/) (2024)
- [Task-Customized Mixture of Adapters for General Image Fusion](https://mlsanity.com/paper/2403.12494/) (2024)
- [A Task-guided, Implicitly-searched and Meta-initialized Deep Model for Image Fusion](https://mlsanity.com/paper/2305.15862/) (2023)
- [Infrared and Visible Image Fusion: From Data Compatibility to Task Adaption](https://mlsanity.com/paper/2501.10761/) (2025)
- [DCEvo: Discriminative Cross-Dimensional Evolutionary Learning for Infrared and Visible Image Fusion](https://mlsanity.com/paper/2503.17673/) (2025)
- [Benchmarking and Comparing Multi-exposure Image Fusion Algorithms](https://mlsanity.com/paper/2007.15156/) (2020)
- [One Model for ALL: Low-Level Task Interaction Is a Key to Task-Agnostic Image Fusion](https://mlsanity.com/paper/2502.19854/) (2025)
- [Text-DiFuse: An Interactive Multi-Modal Image Fusion Framework based on Text-modulated Diffusion Model](https://mlsanity.com/paper/2410.23905/) (2024)
- [Efficient Rectified Flow for Image Fusion](https://mlsanity.com/paper/2509.16549/) (2025)
- [UniFusion: A Unified Image Fusion Framework with Robust Representation and Source-Aware Preservation](https://mlsanity.com/paper/2603.14214/) (2026)

## Abstract (arXiv)

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.