# Fusion from Decomposition: A Self-Supervised Approach for Image Fusion and Beyond arXiv: https://arxiv.org/abs/2410.12274 ยท HTML: https://mlsanity.com/paper/2410.12274/ ## Key facts - Cited by 4 papers in the map (data through 14 Oct 2026). - Builds on 39 of its 71 references that are in the map. - First posted on arXiv 16 Oct 2024. ## Builds on (most cited first, 30 of 39) - [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017) - [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020) - [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020) - [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015) - [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019) - [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021) - [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013) - [Unsupervised Representation Learning by Predicting Image Rotations](https://mlsanity.com/paper/1803.07728/) (2018) - [Unified Perceptual Parsing for Scene Understanding](https://mlsanity.com/paper/1807.10221/) (2018) - [Colorful Image Colorization](https://mlsanity.com/paper/1603.08511/) (2016) - [Unsupervised Visual Representation Learning by Context Prediction](https://mlsanity.com/paper/1505.05192/) (2015) - [Exploring CLIP for Assessing the Look and Feel of Images](https://mlsanity.com/paper/2207.12396/) (2022) - [iBOT: Image BERT Pre-Training with Online Tokenizer](https://mlsanity.com/paper/2111.07832/) (2021) - [Exploring Plain Vision Transformer Backbones for Object Detection](https://mlsanity.com/paper/2203.16527/) (2022) - [Self-supervised Learning: Generative or Contrastive](https://mlsanity.com/paper/2006.08218/) (2020) - [EVA: Exploring the Limits of Masked Visual Representation Learning at Scale](https://mlsanity.com/paper/2211.07636/) (2022) - [Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey](https://mlsanity.com/paper/1902.06162/) (2019) - [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) - [DenseFuse: A Fusion Approach to Infrared and Visible Images](https://mlsanity.com/paper/1804.08361/) (2018) - [Representation Learning by Learning to Count](https://mlsanity.com/paper/1708.06734/) (2017) - [Boosting Self-Supervised Learning via Knowledge Transfer](https://mlsanity.com/paper/1805.00385/) (2018) - [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) - [DeepFuse: A Deep Unsupervised Approach for Exposure Fusion with Extreme Exposure Image Pairs](https://mlsanity.com/paper/1712.07384/) (2017) - [Corrupted Image Modeling for Self-Supervised Visual Pre-Training](https://mlsanity.com/paper/2202.03382/) (2022) - [CoCoNet: Coupled Contrastive Learning Network with Multi-level Feature Ensemble for Multi-modality Image Fusion](https://mlsanity.com/paper/2211.10960/) (2022) - [NestFuse: An Infrared and Visible Image Fusion Architecture based on Nest Connection and Spatial/Channel Attention Models](https://mlsanity.com/paper/2007.00328/) (2020) - [Task-Customized Mixture of Adapters for General Image Fusion](https://mlsanity.com/paper/2403.12494/) (2024) - [A Task-guided, Implicitly-searched and Meta-initialized Deep Model for Image Fusion](https://mlsanity.com/paper/2305.15862/) (2023) ## Built on by (most cited first, 4 of 4) - [Instruction-Driven Fusion of Infrared-Visible Images: Tailoring for Diverse Downstream Tasks](https://mlsanity.com/paper/2411.09387/) (2024) - [Towards Unified Semantic and Controllable Image Fusion: A Diffusion Transformer Approach](https://mlsanity.com/paper/2512.07170/) (2025) - [Customized Fusion: A Closed-Loop Dynamic Network for Adaptive Multi-Task-Aware Infrared-Visible Image Fusion](https://mlsanity.com/paper/2604.08924/) (2026) - [There and Back Again: A Flexible-Frame Transformer for Multi-Exposure Fusion](https://mlsanity.com/paper/2606.27905/) (2026) ## Abstract (arXiv) Image fusion is famous as an alternative solution to generate one high-quality image from multiple images in addition to image restoration from a single degraded image. The essence of image fusion is to integrate complementary information from source images. Existing fusion methods struggle with generalization across various tasks and often require labor-intensive designs, in which it is difficult to identify and extract useful information from source images due to the diverse requirements of each fusion task. Additionally, these methods develop highly specialized features for different downstream applications, hindering the adaptation to new and diverse downstream tasks. To address these limitations, we introduce DeFusion++, a novel framework that leverages self-supervised learning (SSL) to enhance the versatility of feature representation for different image fusion tasks. DeFusion++ captures the image fusion task-friendly representations from large-scale data in a self-supervised way, overcoming the constraints of limited fusion datasets. Specifically, we introduce two innovative pretext tasks: common and unique decomposition (CUD) and masked feature modeling (MFM). CUD decomposes source images into abstract common and unique components, while MFM refines these components into robust fused features. Jointly training of these tasks enables DeFusion++ to produce adaptable representations that can effectively extract useful information from various source images, regardless of the fusion task. The resulting fused representations are also highly adaptable for a wide range of downstream tasks, including image segmentation and object detection. DeFusion++ stands out by producing versatile fused representations that can enhance both the quality of image fusion and the effectiveness of downstream high-level vision tasks, simplifying the process with the elegant fusion framework.