# TransMEF: A Transformer-Based Multi-Exposure Image Fusion Framework using Self-Supervised Multi-Task Learning

arXiv: https://arxiv.org/abs/2112.01030 · HTML: https://mlsanity.com/paper/2112.01030/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 48 references that are in the map.
- First posted on arXiv 2 Dec 2021.

## Builds on (most cited first, 11 of 11)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation](https://mlsanity.com/paper/2102.04306/) (2021)
- [FDA: Fourier Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2004.05498/) (2020)
- [A Fourier-based Framework for Domain Generalization](https://mlsanity.com/paper/2105.11120/) (2021)
- [DenseFuse: A Fusion Approach to Infrared and Visible Images](https://mlsanity.com/paper/1804.08361/) (2018)
- [DeepFuse: A Deep Unsupervised Approach for Exposure Fusion with Extreme Exposure Image Pairs](https://mlsanity.com/paper/1712.07384/) (2017)
- [Benchmarking and Comparing Multi-exposure Image Fusion Algorithms](https://mlsanity.com/paper/2007.15156/) (2020)
- [PatchShuffle Regularization](https://mlsanity.com/paper/1707.07103/) (2017)
- [SESF-Fuse: An Unsupervised Deep Model for Multi-Focus Image Fusion](https://mlsanity.com/paper/1908.01703/) (2019)
- [Deep Exposure Fusion with Deghosting via Homography Estimation and Attention Learning](https://mlsanity.com/paper/2004.09089/) (2020)

## Built on by (most cited first, 30 of 32)

- [Task-Customized Mixture of Adapters for General Image Fusion](https://mlsanity.com/paper/2403.12494/) (2024)
- [Image Fusion via Vision-Language Model](https://mlsanity.com/paper/2402.02235/) (2024)
- [CrossFuse: A Novel Cross Attention Mechanism based Infrared and Visible Image Fusion Approach](https://mlsanity.com/paper/2406.10581/) (2024)
- [SwinFuse: A Residual Swin Transformer Fusion Network for Infrared and Visible Images](https://mlsanity.com/paper/2204.11436/) (2022)
- [MEFLUT: Unsupervised 1D Lookup Tables for Multi-exposure Image Fusion](https://mlsanity.com/paper/2309.11847/) (2023)
- [EMEF: Ensemble Multi-Exposure Image Fusion](https://mlsanity.com/paper/2305.12734/) (2023)
- [TSJNet: A Multi-modality Target and Semantic Awareness Joint-driven Image Fusion Network](https://mlsanity.com/paper/2402.01212/) (2024)
- [Hybrid-Supervised Dual-Search: Leveraging Automatic Learning for Loss-free Multi-Exposure Image Fusion](https://mlsanity.com/paper/2309.01113/) (2023)
- [MMAIF: Multi-task and Multi-degradation All-in-One for Image Fusion with Language Guidance](https://mlsanity.com/paper/2503.14944/) (2025)
- [A Unified Solution to Video Fusion: From Multi-Frame Learning to Benchmarking](https://mlsanity.com/paper/2505.19858/) (2025)
- [Exposure Correction Model to Enhance Image Quality](https://mlsanity.com/paper/2204.10648/) (2022)
- [CrossFuse: Learning Infrared and Visible Image Fusion by Cross-Sensor Top-K Vision Alignment and Beyond](https://mlsanity.com/paper/2502.14493/) (2025)
- [Fusion from Decomposition: A Self-Supervised Approach for Image Fusion and Beyond](https://mlsanity.com/paper/2410.12274/) (2024)
- [SMLNet: A SPD Manifold Learning Network for Infrared and Visible Image Fusion](https://mlsanity.com/paper/2411.10679/) (2024)
- [AdaptiveAE: An Adaptive Exposure Strategy for HDR Capturing in Dynamic Scenes](https://mlsanity.com/paper/2508.13503/) (2025)
- [A Dual Domain Multi-exposure Image Fusion Network based on the Spatial-Frequency Integration](https://mlsanity.com/paper/2312.10604/) (2023)
- [GrFormer: A Novel Transformer on Grassmann Manifold for Infrared and Visible Image Fusion](https://mlsanity.com/paper/2506.14384/) (2025)
- [DePF: A Novel Fusion Approach based on Decomposition Pooling for Infrared and Visible Images](https://mlsanity.com/paper/2305.17376/) (2023)
- [MobileMEF: Fast and Efficient Method for Multi-Exposure Fusion](https://mlsanity.com/paper/2408.07932/) (2024)
- [MambaVF: State Space Model for Efficient Video Fusion](https://mlsanity.com/paper/2602.06017/) (2026)
- [Multi-exposure HDR Imaging: A Review of Pixel-level and Feature-level Reconstruction Methods](https://mlsanity.com/paper/2608.28674/) (2026)
- [Scale-aware Two-stage High Dynamic Range Imaging](https://mlsanity.com/paper/2303.06575/) (2023)
- [Efficient Convolution and Transformer-Based Network for Video Frame Interpolation](https://mlsanity.com/paper/2307.06443/) (2023)
- [Progressive Alignment with VLM-LLM Feature to Augment Defect Classification for the ASE Dataset](https://mlsanity.com/paper/2404.05183/) (2024)
- [Multi-Exposure Image Fusion via Distilled 3D LUT Grid with Editable Mode](https://mlsanity.com/paper/2412.13749/) (2024)
- [SemaMIL: Semantic-Aware Multiple Instance Learning with Retrieval-Guided State Space Modeling for Whole Slide Images](https://mlsanity.com/paper/2509.00442/) (2025)
- [EfficienT-HDR: An Efficient Transformer-Based Framework via Multi-Exposure Fusion for HDR Reconstruction](https://mlsanity.com/paper/2509.19779/) (2025)
- [LoopExpose: An Unsupervised Framework for Arbitrary-Length Exposure Correction](https://mlsanity.com/paper/2511.06066/) (2025)
- [DIFF-MF: A Difference-Driven Channel-Spatial State Space Model for Multi-Modal Image Fusion](https://mlsanity.com/paper/2601.05538/) (2026)
- [FMRFusion: Frequency-Aware Multi-View Representation Learning for Heterogeneous Image Fusion](https://mlsanity.com/paper/2606.07985/) (2026)

## Abstract (arXiv)

In this paper, we propose TransMEF, a transformer-based multi-exposure image fusion framework that uses self-supervised multi-task learning. The framework is based on an encoder-decoder network, which can be trained on large natural image datasets and does not require ground truth fusion images. We design three self-supervised reconstruction tasks according to the characteristics of multi-exposure images and conduct these tasks simultaneously using multi-task learning; through this process, the network can learn the characteristics of multi-exposure images and extract more generalized features. In addition, to compensate for the defect in establishing long-range dependencies in CNN-based architectures, we design an encoder that combines a CNN module with a transformer module. This combination enables the network to focus on both local and global information. We evaluated our method and compared it to 11 competitive traditional and deep learning-based methods on the latest released multi-exposure image fusion benchmark dataset, and our method achieved the best performance in both subjective and objective evaluations.