# DeepFuse: A Deep Unsupervised Approach for Exposure Fusion with Extreme Exposure Image Pairs

arXiv: https://arxiv.org/abs/1712.07384 · HTML: https://mlsanity.com/paper/1712.07384/

## Key facts

- Cited by 78 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Dec 2017.

## Built on by (most cited first, 30 of 78)

- [RFN-Nest: An end-to-end residual fusion network for infrared and visible images](https://mlsanity.com/paper/2103.04286/) (2021)
- [FusionMamba: Dynamic Feature Enhancement for Multimodal Image Fusion with Mamba](https://mlsanity.com/paper/2404.09498/) (2024)
- [Auto-Exposure Fusion for Single-Image Shadow Removal](https://mlsanity.com/paper/2103.01255/) (2021)
- [Ghost-free High Dynamic Range Imaging with Context-aware Transformer](https://mlsanity.com/paper/2208.05114/) (2022)
- [Task-Customized Mixture of Adapters for General Image Fusion](https://mlsanity.com/paper/2403.12494/) (2024)
- [Deep Learning for HDR Imaging: State-of-the-Art and Future Trends](https://mlsanity.com/paper/2110.10394/) (2021)
- [Image Fusion via Vision-Language Model](https://mlsanity.com/paper/2402.02235/) (2024)
- [Multi-Bracket High Dynamic Range Imaging with Event Cameras](https://mlsanity.com/paper/2203.06622/) (2022)
- [TransMEF: A Transformer-Based Multi-Exposure Image Fusion Framework using Self-Supervised Multi-Task Learning](https://mlsanity.com/paper/2112.01030/) (2021)
- [TGFuse: An Infrared and Visible Image Fusion Approach Based on Transformer and Generative Adversarial Network](https://mlsanity.com/paper/2201.10147/) (2022)
- [PAIF: Perception-Aware Infrared-Visible Image Fusion for Attack-Tolerant Semantic Segmentation](https://mlsanity.com/paper/2308.03979/) (2023)
- [Bridging Unsupervised and Supervised Depth from Focus via All-in-Focus Supervision](https://mlsanity.com/paper/2108.10843/) (2021)
- [MEFLUT: Unsupervised 1D Lookup Tables for Multi-exposure Image Fusion](https://mlsanity.com/paper/2309.11847/) (2023)
- [UltraFusion: Ultra High Dynamic Imaging using Exposure Fusion](https://mlsanity.com/paper/2501.11515/) (2025)
- [Single-Image HDR Reconstruction by Multi-Exposure Generation](https://mlsanity.com/paper/2210.15897/) (2022)
- [Mutual-Guided Dynamic Network for Image Fusion](https://mlsanity.com/paper/2308.12538/) (2023)
- [Fast High Dynamic Range Radiance Fields for Dynamic Scenes](https://mlsanity.com/paper/2401.06052/) (2024)
- [FusionBooster: A Unified Image Fusion Boosting Paradigm](https://mlsanity.com/paper/2305.05970/) (2023)
- [Searching a Compact Architecture for Robust Multi-Exposure Image Fusion](https://mlsanity.com/paper/2305.12236/) (2023)
- [EMEF: Ensemble Multi-Exposure Image Fusion](https://mlsanity.com/paper/2305.12734/) (2023)
- [Hybrid-Supervised Dual-Search: Leveraging Automatic Learning for Loss-free Multi-Exposure Image Fusion](https://mlsanity.com/paper/2309.01113/) (2023)
- [A Unified Solution to Video Fusion: From Multi-Frame Learning to Benchmarking](https://mlsanity.com/paper/2505.19858/) (2025)
- [A Dual-branch Network for Infrared and Visible Image Fusion](https://mlsanity.com/paper/2101.09643/) (2021)
- [PPT Fusion: Pyramid Patch Transformerfor a Case Study in Image Fusion](https://mlsanity.com/paper/2107.13967/) (2021)
- [Interactive Feature Embedding for Infrared and Visible Image Fusion](https://mlsanity.com/paper/2211.04877/) (2022)
- [Test-Time Dynamic Image Fusion](https://mlsanity.com/paper/2411.02840/) (2024)
- [Task-Generalized Adaptive Cross-Domain Learning for Multimodal Image Fusion](https://mlsanity.com/paper/2508.15505/) (2025)
- [UFA-FUSE: A novel deep supervised and hybrid model for multi-focus image fusion](https://mlsanity.com/paper/2101.04506/) (2021)
- [TransFuse: A Unified Transformer-based Image Fusion Framework using Self-supervised Learning](https://mlsanity.com/paper/2201.07451/) (2022)
- [Holistic Dynamic Frequency Transformer for Image Fusion and Exposure Correction](https://mlsanity.com/paper/2309.01183/) (2023)

## Abstract (arXiv)

We present a novel deep learning architecture for fusing static multi-exposure images. Current multi-exposure fusion (MEF) approaches use hand-crafted features to fuse input sequence. However, the weak hand-crafted representations are not robust to varying input conditions. Moreover, they perform poorly for extreme exposure image pairs. Thus, it is highly desirable to have a method that is robust to varying input conditions and capable of handling extreme exposure without artifacts. Deep representations have known to be robust to input conditions and have shown phenomenal performance in a supervised setting. However, the stumbling block in using deep learning for MEF was the lack of sufficient training data and an oracle to provide the ground-truth for supervision. To address the above issues, we have gathered a large dataset of multi-exposure image stacks for training and to circumvent the need for ground truth images, we propose an unsupervised deep learning framework for MEF utilizing a no-reference quality metric as loss function. The proposed approach uses a novel CNN architecture trained to learn the fusion operation without reference ground truth image. The model fuses a set of common low level features extracted from each image to generate artifact-free perceptually pleasing results. We perform extensive quantitative and qualitative evaluation and show that the proposed technique outperforms existing state-of-the-art approaches for a variety of natural images.