# Test-Time Dynamic Image Fusion

arXiv: https://arxiv.org/abs/2411.02840 · HTML: https://mlsanity.com/paper/2411.02840/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 64 references that are in the map.
- First posted on arXiv 5 Nov 2024.

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

- [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)
- [LLVIP: A Visible-infrared Paired Dataset for Low-light Vision](https://mlsanity.com/paper/2108.10831/) (2021)
- [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)
- [Trusted Multi-View Classification with Dynamic Evidential Fusion](https://mlsanity.com/paper/2204.11423/) (2022)
- [DDFM: Denoising Diffusion Model for Multi-Modality Image Fusion](https://mlsanity.com/paper/2303.06840/) (2023)
- [Provable Dynamic Fusion for Low-Quality Multimodal Data](https://mlsanity.com/paper/2306.02050/) (2023)
- [DeepFuse: A Deep Unsupervised Approach for Exposure Fusion with Extreme Exposure Image Pairs](https://mlsanity.com/paper/1712.07384/) (2017)
- [DIDFuse: Deep Image Decomposition for Infrared and Visible Image Fusion](https://mlsanity.com/paper/2003.09210/) (2020)
- [Generalization Error Bounds of Gradient Descent for Learning Over-parameterized Deep ReLU Networks](https://mlsanity.com/paper/1902.01384/) (2019)
- [Task-Customized Mixture of Adapters for General Image Fusion](https://mlsanity.com/paper/2403.12494/) (2024)
- [Dynamic Multimodal Fusion](https://mlsanity.com/paper/2204.00102/) (2022)
- [Multi-modal Gated Mixture of Local-to-Global Experts for Dynamic Image Fusion](https://mlsanity.com/paper/2302.01392/) (2023)
- [Medical Image Fusion: A survey of the state of the art](https://mlsanity.com/paper/1401.0166/) (2013)
- [Benchmarking and Comparing Multi-exposure Image Fusion Algorithms](https://mlsanity.com/paper/2007.15156/) (2020)
- [Generalization Bounds via Convex Analysis](https://mlsanity.com/paper/2202.04985/) (2022)
- [SwinFuse: A Residual Swin Transformer Fusion Network for Infrared and Visible Images](https://mlsanity.com/paper/2204.11436/) (2022)
- [SESF-Fuse: An Unsupervised Deep Model for Multi-Focus Image Fusion](https://mlsanity.com/paper/1908.01703/) (2019)
- [Convexified Convolutional Neural Networks](https://mlsanity.com/paper/1609.01000/) (2016)

## Built on by (most cited first, 6 of 6)

- [MMAIF: Multi-task and Multi-degradation All-in-One for Image Fusion with Language Guidance](https://mlsanity.com/paper/2503.14944/) (2025)
- [Dream-IF: Dynamic Relative EnhAnceMent for Image Fusion](https://mlsanity.com/paper/2503.10109/) (2025)
- [Dig2DIG: Dig into Diffusion Information Gains for Image Fusion](https://mlsanity.com/paper/2503.18627/) (2025)
- [SSVIF: Self-Supervised Segmentation-Oriented Visible and Infrared Image Fusion](https://mlsanity.com/paper/2509.22450/) (2025)
- [Reversible Efficient Diffusion for Image Fusion](https://mlsanity.com/paper/2601.20260/) (2026)
- [GateSPINE: Gated Cross-View Fusion for Lumbar Spine MRI Report Generation](https://mlsanity.com/paper/2609.40091/) (2026)

## Abstract (arXiv)

The inherent challenge of image fusion lies in capturing the correlation of multi-source images and comprehensively integrating effective information from different sources. Most existing techniques fail to perform dynamic image fusion while notably lacking theoretical guarantees, leading to potential deployment risks in this field. Is it possible to conduct dynamic image fusion with a clear theoretical justification? In this paper, we give our solution from a generalization perspective. We proceed to reveal the generalized form of image fusion and derive a new test-time dynamic image fusion paradigm. It provably reduces the upper bound of generalization error. Specifically, we decompose the fused image into multiple components corresponding to its source data. The decomposed components represent the effective information from the source data, thus the gap between them reflects the Relative Dominability (RD) of the uni-source data in constructing the fusion image. Theoretically, we prove that the key to reducing generalization error hinges on the negative correlation between the RD-based fusion weight and the uni-source reconstruction loss. Intuitively, RD dynamically highlights the dominant regions of each source and can be naturally converted to the corresponding fusion weight, achieving robust results. Extensive experiments and discussions with in-depth analysis on multiple benchmarks confirm our findings and superiority. Our code is available at https://github.com/Yinan-Xia/TTD.