# When Integral Meets Decomposition: A Signal-Level Self-Supervised Feature Decompose Paradigm for Multi-Modal Image Fusion

arXiv: https://arxiv.org/abs/2609.39004 · HTML: https://mlsanity.com/paper/2609.39004/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 51 references that are in the map.
- First posted on arXiv 30 Sep 2026.

## Builds on (most cited first, 24 of 24)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [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)
- [YOLOv12: Attention-Centric Real-Time Object Detectors](https://mlsanity.com/paper/2502.12524/) (2025)
- [CDDFuse: Correlation-Driven Dual-Branch Feature Decomposition for Multi-Modality Image Fusion](https://mlsanity.com/paper/2211.14461/) (2022)
- [Equivariant Multi-Modality Image Fusion](https://mlsanity.com/paper/2305.11443/) (2023)
- [UniverSeg: Universal Medical Image Segmentation](https://mlsanity.com/paper/2304.06131/) (2023)
- [LRRNet: A Novel Representation Learning Guided Fusion Network for Infrared and Visible Images](https://mlsanity.com/paper/2304.05172/) (2023)
- [Deep Convolutional Neural Network for Multi-modal Image Restoration and Fusion](https://mlsanity.com/paper/1910.04066/) (2019)
- [DIDFuse: Deep Image Decomposition for Infrared and Visible Image Fusion](https://mlsanity.com/paper/2003.09210/) (2020)
- [Task-Customized Mixture of Adapters for General Image Fusion](https://mlsanity.com/paper/2403.12494/) (2024)
- [Self-Supervised Multimodal Learning: A Survey](https://mlsanity.com/paper/2304.01008/) (2023)
- [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)
- [Every SAM Drop Counts: Embracing Semantic Priors for Multi-Modality Image Fusion and Beyond](https://mlsanity.com/paper/2503.01210/) (2025)
- [DCEvo: Discriminative Cross-Dimensional Evolutionary Learning for Infrared and Visible Image Fusion](https://mlsanity.com/paper/2503.17673/) (2025)
- [Text-DiFuse: An Interactive Multi-Modal Image Fusion Framework based on Text-modulated Diffusion Model](https://mlsanity.com/paper/2410.23905/) (2024)
- [Bi-level Dynamic Learning for Jointly Multi-modality Image Fusion and Beyond](https://mlsanity.com/paper/2305.06720/) (2023)
- [Task-driven Image Fusion with Learnable Fusion Loss](https://mlsanity.com/paper/2412.03240/) (2024)
- [DifIISR: A Diffusion Model with Gradient Guidance for Infrared Image Super-Resolution](https://mlsanity.com/paper/2503.01187/) (2025)
- [ReFusion: Learning Image Fusion from Reconstruction with Learnable Loss via Meta-Learning](https://mlsanity.com/paper/2312.07943/) (2023)
- [Conditional Controllable Image Fusion](https://mlsanity.com/paper/2411.01573/) (2024)
- [ControlFusion: A Controllable Image Fusion Framework with Language-Vision Degradation Prompts](https://mlsanity.com/paper/2503.23356/) (2025)
- [BSAFusion: A Bidirectional Stepwise Feature Alignment Network for Unaligned Medical Image Fusion](https://mlsanity.com/paper/2412.08050/) (2024)

## Abstract (arXiv)

Multimodal image fusion (MMIF) aims to integrate complementary information from different modalities into a high-quality fused image and support downstream tasks. Recently, feature decomposition has become an important paradigm by separating source images into common and modality-specific unique features. However, existing methods lack clear supervision because ground-truth (GT) decomposition feature maps are unavailable. They usually combine multiple image-level metrics as losses, which are inherently incomplete and may conflict since each pixel couples attributes such as texture, edge, and contour. To address this, we propose a 1D signal-level self-supervised feature decomposition paradigm. Our core insight is to reformulate feature decomposition from unclear 2D image-level supervision into an integral-driven 1D signal-level optimization problem. This objective-level reformulation uses the 1D signal form to compute the integral constraint. The decomposer is optimized by the integral area between common and original signals, enabling more stable optimization with a clear optimization objective. Our model follows a two-stage SSL framework. Stage I designs dual pretext tasks for integral-driven decomposition at the signal level and structure-preserving reconstruction at the image level. Stage II fuses unique features and combines them with common features to reconstruct the fused image. Experiments on representative MMIF tasks show state-of-the-art (SOTA) performance. Code: github.com/Wangjiayu0512/SIDFusion.