# Distilling Textual Priors from LLM to Efficient Image Fusion

arXiv: https://arxiv.org/abs/2504.07029 · HTML: https://mlsanity.com/paper/2504.07029/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 50 references that are in the map.
- First posted on arXiv 9 Apr 2025.

## Builds on (most cited first, 25 of 25)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery](https://mlsanity.com/paper/2103.17249/) (2021)
- [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)
- [DDFM: Denoising Diffusion Model for Multi-Modality Image Fusion](https://mlsanity.com/paper/2303.06840/) (2023)
- [TinyCLIP: CLIP Distillation via Affinity Mimicking and Weight Inheritance](https://mlsanity.com/paper/2309.12314/) (2023)
- [Text-IF: Leveraging Semantic Text Guidance for Degradation-Aware and Interactive Image Fusion](https://mlsanity.com/paper/2403.16387/) (2024)
- [Lite Vision Transformer with Enhanced Self-Attention](https://mlsanity.com/paper/2112.10809/) (2021)
- [Task-Customized Mixture of Adapters for General Image Fusion](https://mlsanity.com/paper/2403.12494/) (2024)
- [A Comparative Study of Image Restoration Networks for General Backbone Network Design](https://mlsanity.com/paper/2310.11881/) (2023)
- [Multi-modal Gated Mixture of Local-to-Global Experts for Dynamic Image Fusion](https://mlsanity.com/paper/2302.01392/) (2023)
- [Benchmarking Micro-action Recognition: Dataset, Methods, and Applications](https://mlsanity.com/paper/2403.05234/) (2024)
- [MobileViTv3: Mobile-Friendly Vision Transformer with Simple and Effective Fusion of Local, Global and Input Features](https://mlsanity.com/paper/2209.15159/) (2022)
- [MobileDiffusion: Instant Text-to-Image Generation on Mobile Devices](https://mlsanity.com/paper/2311.16567/) (2023)
- [TextFusion: Unveiling the Power of Textual Semantics for Controllable Image Fusion](https://mlsanity.com/paper/2312.14209/) (2023)
- [Image Fusion in Remote Sensing: An Overview and Meta Analysis](https://mlsanity.com/paper/2401.08837/) (2024)

## Built on by (most cited first, 1 of 1)

- [Hybrid Fusion: One-Minute Efficient Training for Zero-Shot Cross-Domain Image Fusion](https://mlsanity.com/paper/2602.20851/) (2026)

## Abstract (arXiv)

Multi-modality image fusion aims to synthesize a single, comprehensive image from multiple source inputs. Traditional approaches, such as CNNs and GANs, offer efficiency but struggle to handle low-quality or complex inputs. Recent advances in text-guided methods leverage large model priors to overcome these limitations, but at the cost of significant computational overhead, both in memory and inference time. To address this challenge, we propose a novel framework for distilling large model priors, eliminating the need for text guidance during inference while dramatically reducing model size. Our framework utilizes a teacher-student architecture, where the teacher network incorporates large model priors and transfers this knowledge to a smaller student network via a tailored distillation process. Additionally, we introduce spatial-channel cross-fusion module to enhance the model's ability to leverage textual priors across both spatial and channel dimensions. Our method achieves a favorable trade-off between computational efficiency and fusion quality. The distilled network, requiring only 10% of the parameters and inference time of the teacher network, retains 90% of its performance and outperforms existing SOTA methods. Extensive experiments demonstrate the effectiveness of our approach. The implementation will be made publicly available as an open-source resource.