{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/densefuse-a-fusion-approach-to-infrared-and","title":"DenseFuse: A Fusion Approach to Infrared and Visible Images","arxiv_id":"1804.08361","date":"2018-04-23","proceeding":null,"authors":["Hui Li","Xiao-Jun Wu"],"abstract":"In this paper, we present a novel deep learning architecture for infrared and\nvisible images fusion problem. In contrast to conventional convolutional\nnetworks, our encoding network is combined by convolutional layers, fusion\nlayer and dense block in which the output of each layer is connected to every\nother layer. We attempt to use this architecture to get more useful features\nfrom source images in encoding process. And two fusion layers(fusion\nstrategies) are designed to fuse these features. Finally, the fused image is\nreconstructed by decoder. Compared with existing fusion methods, the proposed\nfusion method achieves state-of-the-art performance in objective and subjective\nassessment. Code and pre-trained models are available at\nhttps://github.com/hli1221/imagefusion_densefuse","url_abs":"http://arxiv.org/abs/1804.08361v9","url_pdf":"http://arxiv.org/pdf/1804.08361v9.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"densefuse-a-fusion-approach-to-infrared-and","repo_url":"https://github.com/exceptionLi/imagefusion_densefuse","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"densefuse-a-fusion-approach-to-infrared-and","repo_url":"https://github.com/hli1221/imagefusion_densefuse","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"densefuse-a-fusion-approach-to-infrared-and","repo_url":"https://github.com/bupt-ai-cz/LLVIP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"densefuse-a-fusion-approach-to-infrared-and","repo_url":"https://github.com/hli1221/densefuse-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"}],"methods":[{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-block","method_name":"Dense Block"},{"method_slug":"relu","method_name":"ReLU"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1804.08361","atlas_url":"https://app.syntology.ai/?focus=1804.08361","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}