Papers
Topics
Authors
Recent
Search
2000 character limit reached

Little Strokes Fell Great Oaks: Boosting the Hierarchical Features for Multi-exposure Image Fusion

Published 9 Apr 2024 in cs.CV | (2404.06033v2)

Abstract: In recent years, deep learning networks have made remarkable strides in the domain of multi-exposure image fusion. Nonetheless, prevailing approaches often involve directly feeding over-exposed and under-exposed images into the network, which leads to the under-utilization of inherent information present in the source images. Additionally, unsupervised techniques predominantly employ rudimentary weighted summation for color channel processing, culminating in an overall desaturated final image tone. To partially mitigate these issues, this study proposes a gamma correction module specifically designed to fully leverage latent information embedded within source images. Furthermore, a modified transformer block, embracing with self-attention mechanisms, is introduced to optimize the fusion process. Ultimately, a novel color enhancement algorithm is presented to augment image saturation while preserving intricate details. The source code is available at https://github.com/ZhiyingDu/BHFMEF.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (49)
  1. Learning a deep single image contrast enhancer from multi-exposure images. IEEE Transactions on Image Processing 27, 4 (2018), 2049–2062.
  2. Crighton, D. G. Basic principles of aerodynamic noise generation. Progress in Aerospace Sciences 16, 1 (1975), 31–96.
  3. Artifact-free high dynamic range imaging. In 2009 IEEE International conference on computational photography (ICCP) (2009), IEEE, pp. 1–7.
  4. Zero-reference deep curve estimation for low-light image enhancement. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (2020), pp. 1780–1789.
  5. Multi-exposure image fusion via deep perceptual enhancement. Information Fusion 79 (2022), 248–262.
  6. Comments on’information measure for performance of image fusion’.
  7. A generative adversarial network for infrared and visible image fusion based on semantic segmentation. Entropy 23, 3 (2021), 376.
  8. Exposure normalization and compensation for multiple-exposure correction. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (June 2022), pp. 6043–6052.
  9. Deep fourier-based exposure correction network with spatial-frequency interaction. In Proceedings of the European Conference on Computer Vision (ECCV) (2022).
  10. Exposure-consistency representation learning for exposure correction. In Proceedings of the 30th ACM International Conference on Multimedia (2022), p. 6309–6317.
  11. A review of quality metrics for fused image. Aquatic Procedia 4 (2015), 133–142.
  12. An improved gamma correction model for image dehazing in a multi-exposure fusion framework. Journal of Visual Communication and Image Representation 78 (2021), 103122.
  13. Galfusion: Multi-exposure image fusion via a global–local aggregation learning network. IEEE Transactions on Instrumentation and Measurement 72 (2023), 1–15.
  14. Fast multi-scale structural patch decomposition for multi-exposure image fusion. IEEE Transactions on Image Processing 29 (2020), 5805–5816.
  15. Learning a coordinated network for detail-refinement multiexposure image fusion. IEEE Transactions on Circuits and Systems for Video Technology 33, 2 (2022), 713–727.
  16. Image fusion with guided filtering. IEEE Transactions on Image processing 22, 7 (2013), 2864–2875.
  17. Attention-guided global-local adversarial learning for detail-preserving multi-exposure image fusion. IEEE Transactions on Circuits and Systems for Video Technology 32, 8 (2022), 5026–5040.
  18. Holoco: Holistic and local contrastive learning network for multi-exposure image fusion. Information Fusion 95 (2023), 237–249.
  19. A bilevel integrated model with data-driven layer ensemble for multi-modality image fusion. IEEE Transactions on Image Processing 30 (2020), 1261–1274.
  20. Learning with nested scene modeling and cooperative architecture search for low-light vision. IEEE Transactions on Pattern Analysis and Machine Intelligence 45, 5 (2022), 5953–5969.
  21. Retinex-inspired unrolling with cooperative prior architecture search for low-light image enhancement. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2021), pp. 10561–10570.
  22. Investigating task-driven latent feasibility for nonconvex image modeling. IEEE Transactions on Image Processing 29 (2020), 7629–7640.
  23. Dense sift for ghost-free multi-exposure fusion. Journal of Visual Communication and Image Representation 31 (2015), 208–224.
  24. Swinfusion: Cross-domain long-range learning for general image fusion via swin transformer. IEEE/CAA Journal of Automatica Sinica 9, 7 (2022), 1200–1217.
  25. Deep guided learning for fast multi-exposure image fusion. IEEE Transactions on Image Processing 29 (2019), 2808–2819.
  26. Robust multi-exposure image fusion: a structural patch decomposition approach. IEEE Transactions on Image Processing 26, 5 (2017), 2519–2532.
  27. Multi-exposure image fusion: A patch-wise approach. In 2015 IEEE International Conference on Image Processing (ICIP) (2015), pp. 1717–1721.
  28. Perceptual quality assessment for multi-exposure image fusion. IEEE Transactions on Image Processing 24, 11 (2015), 3345–3356.
  29. Triple-level model inferred collaborative network architecture for video deraining. IEEE Transactions on Image Processing 31 (2021), 239–250.
  30. A binocular image fusion approach for minimizing false positives in handgun detection with deep learning. Inf. Fusion 49 (2019), 271–280.
  31. Two-exposure image fusion based on optimized adaptive gamma correction. Sensors 22, 1 (2021), 24.
  32. Multifocus and multispectral image fusion based on pixel significance using multiresolution decomposition. Signal, Image and Video Processing 7 (2013), 95–109.
  33. Generalized random walks for fusion of multi-exposure images. IEEE Transactions on Image Processing 20, 12 (2011), 3634–3646.
  34. Multi-view image fusion. In 2019 IEEE/CVF International Conference on Computer Vision (ICCV) (2019), pp. 4100–4109.
  35. Exposure fusion based on shift-invariant discrete wavelet transform *. Journal of Information Science and Engineering 27 (2011), 197–211.
  36. A nonlinear correlation measure for multivariable data set. Physica D: Nonlinear Phenomena 200, 3 (2005), 287–295.
  37. Early convolutions help transformers see better. Advances in Neural Information Processing Systems 34 (2021), 30392–30400.
  38. U2fusion: A unified unsupervised image fusion network. IEEE Transactions on Pattern Analysis and Machine Intelligence 44, 1 (2020), 502–518.
  39. Fusiondn: A unified densely connected network for image fusion. In Proceedings of the AAAI conference on artificial intelligence (2020), vol. 34, pp. 12484–12491.
  40. Mef-gan: Multi-exposure image fusion via generative adversarial networks. IEEE Transactions on Image Processing 29 (2020), 7203–7216.
  41. A reference-free underwater image quality assessment metric in frequency domain. Signal Processing: Image Communication 94 (2021), 116218.
  42. Automatic exposure correction of consumer photographs. In Computer Vision–ECCV 2012: 12th European Conference on Computer Vision, Florence, Italy, October 7-13, 2012, Proceedings, Part IV 12 (2012), Springer, pp. 771–785.
  43. Sdnet: A versatile squeeze-and-decomposition network for real-time image fusion. International Journal of Computer Vision 129 (2021), 2761–2785.
  44. Image fusion meets deep learning: A survey and perspective. Information Fusion 76 (2021), 323–336.
  45. Structure- and texture-aware learning for low-light image enhancement. In Proceedings of the 30th ACM International Conference on Multimedia (2022), p. 6483–6492.
  46. Ffdnet: Toward a fast and flexible solution for cnn-based image denoising. IEEE Transactions on Image Processing 27, 9 (2018), 4608–4622.
  47. Zhang, X. Benchmarking and comparing multi-exposure image fusion algorithms. Information Fusion 74 (2021), 111–131.
  48. Ifcnn: A general image fusion framework based on convolutional neural network. Information Fusion 54 (2020), 99–118.
  49. Efficient and model-based infrared and visible image fusion via algorithm unrolling. IEEE Transactions on Circuits and Systems for Video Technology 32, 3 (2021), 1186–1196.
Citations (3)
View on Semantic Scholar

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now

Authors (4)

  1. Pan Mu 
  2. Zhiying Du 
  3. Jinyuan Liu 
  4. Cong Bai 

Collections

Sign up for free to add this paper to one or more collections.

Sign Up

Tweets

Sign up for free to view the 1 tweet with 0 likes about this paper.

Sign Up for Free