Full search page →

Training signals of representative fusion networks

Optional · supplementary note 5 of 6 for DLCV 10 · Image Fusion: Complementary Images, Useful Outputs. Nothing in the main text depends on it; citation numbers refer to the reference list at the bottom of this page.

Navigate: this page and this track: Navigate: this page and this track

On this page

Supplementary notes · 6

  1. The defocus spread effect
  2. Building and collapsing a Laplacian pyramid
  3. Sparse-representation fusion
  4. Mutual information as a fusion metric
  5. Training signals of representative fusion networks
  6. VIF and source-referenced fusion scores

Paper guides · 11

  1. Exposure fusion (Mertens, Kautz and Van Reeth)
  2. VIFB: a visible and infrared image fusion benchmark
  3. The infrared–visible fusion survey of Liu et al. (TPAMI 2025)
  4. DenseFuse: learn reconstruction, choose fusion in feature space
  5. DDFM: a diffusion prior with likelihood rectification
  6. FusionGAN: thermal intensity with an adversarial visible-image prior
  7. IFCNN: supervised fusion with a variable number of inputs
  8. U2Fusion: one unsupervised model across fusion tasks
  9. SwinFusion: attention within and across the sources
  10. SeAFusion: let semantic segmentation influence the fused image
  11. TarDAL: fuse for both appearance and object detection

Deep Learning for Computer Vision

  1. 02 · Deep Image Classification
View the whole course tree →

This note compares what representative deep fusion networks are trained to do: with no ground-truth fused image, the training signal, more than the architecture, decides what the output looks like.

Reconstruction, then a fixed rule (DenseFuse). The encoder–decoder of DenseFuse [30] is trained only to reconstruct visible images, with a loss L=λLssim+Lp\mathcal{L} = \lambda \mathcal{L}_{\text{ssim}} + \mathcal{L}_p, where Lp\mathcal{L}_p is a pixel loss between output and input, Lssim=1−SSIM(O,I)\mathcal{L}_{\text{ssim}} = 1 - \mathrm{SSIM}(O, I) the structural loss between output OO and input II, and λ\lambda their balance. At test time both sources are encoded and their feature maps are merged either by addition or by an ℓ1\ell_1-norm-based strategy that weights each source’s features by their activity, and the decoder turns the merged features into the fused image. Implication: the network never sees a fusion example; the fusion rule is as hand-made as in classical methods, only applied to learned features instead of pyramid coefficients.

A perceptual quality index as the loss (DeepFuse). DeepFuse [31] converts the exposures to YCbCr, fuses the luminance channels with a CNN whose loss is MEF-SSIM [25] computed between the fused luminance and the input stack, and fuses the chroma channels with a weighted rule outside the network. MEF-SSIM compares the structure of each fused patch with a desired structure built from the input patches, so the network needs no reference image. Implication: the network learns MEF-SSIM’s notion of quality, including whatever MEF-SSIM does not see; a good MEF-SSIM score after training is partly a statement about the loss, not an independent confirmation.

Adaptive weights from the sources (U2Fusion). U2Fusion [32] extracts features of each source, measures how much information they contain, and turns the measurement into adaptive preservation degrees that weight a similarity loss between the fused image and each source. Because the degrees are computed per image pair, the same loss works for multi-modal, multi-exposure and multi-focus inputs, and one network is trained on the tasks in sequence while avoiding the loss of what it learned earlier. Implication: the definition of the answer moves from a fixed weight to a measurement; the result is as good as the information measure is at saying which source matters where.

Hand-balanced terms (SwinFusion). SwinFusion [34] uses an SSIM loss, a texture loss and an intensity loss, and models long-range dependencies with self-attention within each source and cross-attention between them. Implication: the three weights trade structure, texture and brightness against each other, exactly as λ\lambda did for the loss minimizer of the main text.

An adversary (FusionGAN). In FusionGAN [39] the generator is pushed by its content loss toward the infrared intensities plus the visible gradients, and a discriminator that compares the fused image with visible images pushes it to contain more visible detail. The authors describe their results as looking like sharpened infrared images with clearly highlighted targets [39]. Implication: the discriminator supplies a learned notion of “visible-looking detail”, but adversarial training can also add detail that is in neither source; TarDAL later used two discriminators, one per modality [27].

A decomposition constraint (CDDFuse). CDDFuse [38] extracts low-frequency, global features with transformer blocks and high-frequency, local features with invertible blocks, and adds a correlation-driven loss that makes the low-frequency features of the two modalities correlated and their high-frequency features uncorrelated. Implication: the loss encodes a model of the data, shared base and modality-specific detail, which is the learned counterpart of the base/detail split of classical fusion.

No fusion training at all (DDFM). DDFM [41] formulates fusion as conditional generation under a denoising diffusion sampler: an unconditional diffusion model pretrained on natural images supplies the prior, and at each sampling step a maximum-likelihood subproblem, modeled with latent variables and solved by expectation–maximization, pulls the sample toward consistency with both sources. Implication: the “loss” becomes a statistical model of how the fused image relates to the sources, plus a generative prior that keeps the result natural-looking; no fine-tuning of the diffusion model is needed, but sampling is iterative and therefore much slower than one forward pass of a network.

A self-supervised imaging prior (EMMA). EMMA [52] trains a fusion module together with a pseudo-sensing module that imitates how the sensors would image the fused scene, and requires the whole loop to behave consistently under transformations to which natural imaging is equivariant. Implication: instead of hand-weighting terms, the training signal asks that the fused image could have produced the sources, an idea close to cycle consistency.

Summary.

MethodWhat is optimizedWhat decides the fused image
DenseFuseImage reconstructionA hand-made feature-merging rule
DeepFuseMEF-SSIM on the luminanceMEF-SSIM’s model of quality
U2FusionSimilarity to sources, adaptively weightedAn information measure on features
SwinFusionSSIM + texture + intensityThe three loss weights
FusionGANContent loss + adversarial lossInfrared intensity, visible gradients and a discriminator
CDDFuseIncludes a correlation-driven decomposition lossA shared-base / specific-detail model
DDFMNothing (no fusion training)A pretrained diffusion prior + a likelihood model
EMMASelf-supervised equivariant consistencyConsistency between fused image and sources

References

  1. Y. Liu, X. Chen, Z. Wang, Z. J. Wang, R. K. Ward and X. Wang, “Deep learning for pixel-level image fusion: Recent advances and future prospects,” Information Fusion, vol. 42, pp. 158–173, 2018. doi
  2. J. Liu, G. Wu, Z. Liu, D. Wang, Z. Jiang, L. Ma, W. Zhong, X. Fan and R. Liu, “Infrared and visible image fusion: From data compatibility to task adaption,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 47, no. 4, pp. 2349–2369, 2025. doi arXiv
  3. J. Ma, Y. Ma and C. Li, “Infrared and visible image fusion methods and applications: A survey,” Information Fusion, vol. 45, pp. 153–178, 2019. doi
  4. P. E. Debevec and J. Malik, “Recovering high dynamic range radiance maps from photographs,” in Proc. SIGGRAPH, 1997, pp. 369–378. doi
  5. T. Mertens, J. Kautz and F. Van Reeth, “Exposure fusion: A simple and practical alternative to high dynamic range photography,” Computer Graphics Forum, vol. 28, no. 1, pp. 161–171, 2009. doi
  6. S. Xu, X. Wei, C. Zhang, J. Liu and J. Zhang, “MFFW: A new dataset for multi-focus image fusion,” arXiv:2002.04780, 2020. arXiv
  7. X. Zhang, “Multi-focus image fusion: A benchmark,” arXiv:2005.01116, 2020. arXiv
  8. P. J. Burt and E. H. Adelson, “The Laplacian pyramid as a compact image code,” IEEE Transactions on Communications, vol. 31, no. 4, pp. 532–540, 1983. doi
  9. P. J. Burt and R. J. Kolczynski, “Enhanced image capture through fusion,” in Proc. 4th International Conference on Computer Vision (ICCV), 1993, pp. 173–182. doi
  10. P. J. Burt and E. H. Adelson, “A multiresolution spline with application to image mosaics,” ACM Transactions on Graphics, vol. 2, no. 4, pp. 217–236, 1983. doi
  11. H. Li, B. S. Manjunath and S. K. Mitra, “Multisensor image fusion using the wavelet transform,” Graphical Models and Image Processing, vol. 57, no. 3, pp. 235–245, 1995. doi
  12. S. Li, X. Kang and J. Hu, “Image fusion with guided filtering,” IEEE Transactions on Image Processing, vol. 22, no. 7, pp. 2864–2875, 2013. doi
  13. K. He, J. Sun and X. Tang, “Guided image filtering,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 35, no. 6, pp. 1397–1409, 2013. doi
  14. B. Yang and S. Li, “Multifocus image fusion and restoration with sparse representation,” IEEE Transactions on Instrumentation and Measurement, vol. 59, no. 4, pp. 884–892, 2010. doi
  15. M. Nejati, S. Samavi and S. Shirani, “Multi-focus image fusion using dictionary-based sparse representation,” Information Fusion, vol. 25, pp. 72–84, 2015. doi
  16. Z. Wang, A. C. Bovik, H. R. Sheikh and E. P. Simoncelli, “Image quality assessment: From error visibility to structural similarity,” IEEE Transactions on Image Processing, vol. 13, no. 4, pp. 600–612, 2004. doi
  17. X. Zhang, P. Ye and G. Xiao, “VIFB: A visible and infrared image fusion benchmark,” in Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2020. CVF arXiv
  18. X. Zhang, “Benchmarking and comparing multi-exposure image fusion algorithms,” Information Fusion, vol. 74, pp. 111–131, 2021. doi arXiv
  19. A. M. Eskicioglu and P. S. Fisher, “Image quality measures and their performance,” IEEE Transactions on Communications, vol. 43, no. 12, pp. 2959–2965, 1995. doi
  20. G. Qu, D. Zhang and P. Yan, “Information measure for performance of image fusion,” Electronics Letters, vol. 38, no. 7, pp. 313–315, 2002. doi
  21. M. Hossny, S. Nahavandi and D. Creighton, “Comments on ‘Information measure for performance of image fusion’,” Electronics Letters, vol. 44, no. 18, pp. 1066–1067, 2008. doi
  22. C. S. Xydeas and V. Petrović, “Objective image fusion performance measure,” Electronics Letters, vol. 36, no. 4, pp. 308–309, 2000. doi
  23. G. Piella and H. Heijmans, “A new quality metric for image fusion,” in Proc. IEEE International Conference on Image Processing (ICIP), 2003, vol. 3, pp. III-173–176. doi
  24. Y. Han, Y. Cai, Y. Cao and X. Xu, “A new image fusion performance metric based on visual information fidelity,” Information Fusion, vol. 14, no. 2, pp. 127–135, 2013. doi
  25. K. Ma, K. Zeng and Z. Wang, “Perceptual quality assessment for multi-exposure image fusion,” IEEE Transactions on Image Processing, vol. 24, no. 11, pp. 3345–3356, 2015. doi
  26. Z. Liu, E. Blasch, Z. Xue, J. Zhao, R. Laganiere and W. Wu, “Objective assessment of multiresolution image fusion algorithms for context enhancement in night vision: A comparative study,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 34, no. 1, pp. 94–109, 2012. doi
  27. J. Liu, X. Fan, Z. Huang, G. Wu, R. Liu, W. Zhong and Z. Luo, “Target-aware dual adversarial learning and a multi-scenario multi-modality benchmark to fuse infrared and visible for object detection,” in Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 5802–5811. CVF arXiv M3FD
  28. J. Liu, Z. Liu, G. Wu, L. Ma, R. Liu, W. Zhong, Z. Luo and X. Fan, “Multi-interactive feature learning and a full-time multi-modality benchmark for image fusion and segmentation,” in Proc. IEEE/CVF International Conference on Computer Vision (ICCV), 2023, pp. 8115–8124. CVF arXiv
  29. Y. Zhang, Y. Liu, P. Sun, H. Yan, X. Zhao and L. Zhang, “IFCNN: A general image fusion framework based on convolutional neural network,” Information Fusion, vol. 54, pp. 99–118, 2020. doi
  30. H. Li and X.-J. Wu, “DenseFuse: A fusion approach to infrared and visible images,” IEEE Transactions on Image Processing, vol. 28, no. 5, pp. 2614–2623, 2019. doi arXiv
  31. K. R. Prabhakar, V. S. Srikar and R. V. Babu, “DeepFuse: A deep unsupervised approach for exposure fusion with extreme exposure image pairs,” in Proc. IEEE International Conference on Computer Vision (ICCV), 2017, pp. 4724–4732. doi CVF
  32. H. Xu, J. Ma, J. Jiang, X. Guo and H. Ling, “U2Fusion: A unified unsupervised image fusion network,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 44, no. 1, pp. 502–518, 2022. doi RoadScene
  33. L. Tang, J. Yuan and J. Ma, “Image fusion in the loop of high-level vision tasks: A semantic-aware real-time infrared and visible image fusion network,” Information Fusion, vol. 82, pp. 28–42, 2022. doi
  34. J. Ma, L. Tang, F. Fan, J. Huang, X. Mei and Y. Ma, “SwinFusion: Cross-domain long-range learning for general image fusion via Swin Transformer,” IEEE/CAA Journal of Automatica Sinica, vol. 9, no. 7, pp. 1200–1217, 2022. doi
  35. X. Zhang and Y. Demiris, “Visible and infrared image fusion using deep learning,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 45, no. 8, pp. 10535–10554, 2023. doi
  36. Y. Liu, X. Chen, H. Peng and Z. Wang, “Multi-focus image fusion with a deep convolutional neural network,” Information Fusion, vol. 36, pp. 191–207, 2017. doi
  37. K. Ma, Z. Duanmu, H. Zhu, Y. Fang and Z. Wang, “Deep guided learning for fast multi-exposure image fusion,” IEEE Transactions on Image Processing, vol. 29, pp. 2808–2819, 2020. doi
  38. Z. Zhao, H. Bai, J. Zhang, Y. Zhang, S. Xu, Z. Lin, R. Timofte and L. Van Gool, “CDDFuse: Correlation-driven dual-branch feature decomposition for multi-modality image fusion,” in Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023, pp. 5906–5916. CVF arXiv
  39. J. Ma, W. Yu, P. Liang, C. Li and J. Jiang, “FusionGAN: A generative adversarial network for infrared and visible image fusion,” Information Fusion, vol. 48, pp. 11–26, 2019. doi · public article transcription
  40. H. Bai, J. Zhang, Z. Zhao, Y. Wu, L. Deng, Y. Cui, T. Feng and S. Xu, “Task-driven image fusion with learnable fusion loss,” in Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025, pp. 7457–7468. CVF arXiv
  41. Z. Zhao, H. Bai, Y. Zhu, J. Zhang, S. Xu, Y. Zhang, K. Zhang, D. Meng, R. Timofte and L. Van Gool, “DDFM: Denoising diffusion model for multi-modality image fusion,” in Proc. IEEE/CVF International Conference on Computer Vision (ICCV), 2023, pp. 8082–8093. CVF arXiv
  42. X. Yi, H. Xu, H. Zhang, L. Tang and J. Ma, “Text-IF: Leveraging semantic text guidance for degradation-aware and interactive image fusion,” in Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024, pp. 27026–27035. CVF arXiv
  43. D. Wang, J. Liu, X. Fan and R. Liu, “Unsupervised misaligned infrared and visible image fusion via cross-modality image generation and registration,” in Proc. International Joint Conference on Artificial Intelligence (IJCAI), 2022, pp. 3508–3515. doi arXiv
  44. L. Tang, Y. Deng, Y. Ma, J. Huang and J. Ma, “SuperFusion: A versatile image registration and fusion network with semantic awareness,” IEEE/CAA Journal of Automatica Sinica, vol. 9, no. 12, pp. 2121–2137, 2022. doi
  45. A. Toet, “The TNO multiband image data collection,” Data in Brief, vol. 15, pp. 249–251, 2017. doi
  46. L. Tang, J. Yuan, H. Zhang, X. Jiang and J. Ma, “PIAFusion: A progressive infrared and visible image fusion network based on illumination aware,” Information Fusion, vol. 83–84, pp. 79–92, 2022. doi MSRS
  47. Q. Ha, K. Watanabe, T. Karasawa, Y. Ushiku and T. Harada, “MFNet: Towards real-time semantic segmentation for autonomous vehicles with multi-spectral scenes,” in Proc. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2017, pp. 5108–5115. doi
  48. X. Jia, C. Zhu, M. Li, W. Tang and W. Zhou, “LLVIP: A visible-infrared paired dataset for low-light vision,” in Proc. IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, 2021, pp. 3496–3504. CVF arXiv
  49. J. Cai, S. Gu and L. Zhang, “Learning a deep single image contrast enhancer from multi-exposure images,” IEEE Transactions on Image Processing, vol. 27, no. 4, pp. 2049–2062, 2018. doi
  50. X. Zhang, “Deep learning-based multi-focus image fusion: A survey and a comparative study,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 44, no. 9, 2022. doi
  51. F. Xu, J. Liu, Y. Song, H. Sun and X. Wang, “Multi-exposure image fusion techniques: A comprehensive review,” Remote Sensing, vol. 14, no. 3, art. 771, 2022. doi
  52. Z. Zhao, H. Bai, J. Zhang, Y. Zhang, K. Zhang, S. Xu, D. Chen, R. Timofte and L. Van Gool, “Equivariant multi-modality image fusion,” in Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024, pp. 25912–25921. CVF arXiv
  53. L. Tang, Y. Wang, M. Gong, Z. Li, Y. Deng, X. Yi, C. Li, H. Xu, H. Zhang and J. Ma, “VideoFusion: A spatio-temporal collaborative network for multi-modal video fusion,” in Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026, pp. 19559–19569. CVF
  54. N. Yokoya, C. Grohnfeldt and J. Chanussot, “Hyperspectral and multispectral data fusion: A comparative review of the recent literature,” IEEE Geoscience and Remote Sensing Magazine, 2017. doi
  55. H. R. Sheikh and A. C. Bovik, “Image information and visual quality,” IEEE Transactions on Image Processing, 2006. doi
  56. H. Xu et al., “U2Fusion,” official implementation accompanying the TPAMI paper, 2022. code
  57. K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” ICLR, 2015. arXiv
  58. J. Kirkpatrick et al., “Overcoming catastrophic forgetting in neural networks,” Proceedings of the National Academy of Sciences, 2017. doi
  59. Y. Zhang et al., “IFCNN,” official implementation and errata accompanying the Information Fusion paper, 2020. code
  60. K. He, X. Zhang, S. Ren and J. Sun, “Deep residual learning for image recognition,” CVPR, 2016. CVF
  61. J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li and L. Fei-Fei, “ImageNet: A large-scale hierarchical image database,” CVPR, 2009. doi
  62. N. Silberman, D. Hoiem, P. Kohli and R. Fergus, “Indoor segmentation and support inference from RGBD images,” ECCV, 2012. project
  63. P. Dhariwal and A. Nichol, “Diffusion models beat GANs on image synthesis,” NeurIPS, 2021. arXiv
  64. J. Liu et al., “TarDAL,” official implementation accompanying the CVPR paper, 2022. code
  65. G. Jocher et al., “YOLOv5,” Ultralytics object-detection software, 2020 onward. code
  66. J. Ma et al., “FusionGAN,” official implementation accompanying the Information Fusion paper, 2019. code
  67. L. Tang, J. Yuan and J. Ma, “SeAFusion,” official implementation accompanying the Information Fusion paper, 2022. code
  68. T. Mertens, J. Kautz and F. Van Reeth, “Exposure Fusion,” in Proc. Pacific Graphics, 2007. paper · author project