A Review Toward Deep Learning for High Dynamic Range Reconstruction
Source abstract
Abstract
High Dynamic Range (HDR) image reconstruction has gained prominence in a wide range of fields; not only is it implemented in computer vision, but industries such as entertainment and medicine also benefit considerably from this technology due to its ability to capture and reproduce scenes with a greater variety of luminosities, extending conventional levels of perception. This article presents a review of the state of the art of HDR reconstruction methods based on deep learning, ranging from classical approaches that are still expressive and relevant to more recent proposals involving the advent of new architectures. The fundamental role of high-quality datasets and specific metrics in evaluating the performance of HDR algorithms is also discussed, as well as emphasizing the challenges inherent in capturing multiple exposures and dealing with artifacts. Finally, emerging trends and promising directions for overcoming current limitations and expanding the potential of HDR reconstruction in real-world scenarios are highlighted.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Image Processing Techniques · Image Enhancement Techniques · Image and Signal Denoising Methods
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
PAVIC Laboratory, University of Acre (UFAC), Rio Branco 69915-900, Brazil
Funding
PAVIC Laboratory
References (100+)
Show source-provided references
1. Ferreti, G.d.S., Paixão, T., and Alvarez, A.B. (2025). Generative Adversarial Network-Based Lightweight High-Dynamic-Range Image Reconstruction Model. Appl. Sci., 15.10.3390/app15094801 ↗
2. Lopez-Cabrejos, J., Paixão, T., Alvarez, A.B., and Luque, D.B. (2025). An Efficient and Low-Complexity Transformer-Based Deep Learning Framework for High-Dynamic-Range Image Reconstruction. Sensors, 25.10.3390/s25051497 ↗
3. Fuest, M., Ma, P., Gui, M., Fischer, J.S., Hu, V.T., and Ommer, B. (2024). Diffusion Models and Representation Learning: A Survey. arXiv.
4. Zhu, R., Xu, S., Liu, P., Li, S., Lu, Y., Niu, D., Liu, Z., Meng, Z., Li, Z., and Chen, X. (2024, January 16–22). Zero-Shot Structure-Preserving Diffusion Model for High Dynamic Range Tone Mapping. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR52733.2024.02469 ↗
5. Beckmann, M., Krahmer, F., and Bhandari, A. (2020, January 25–28). HDR tomography via modulo Radon transform. Proceedings of the 2020 IEEE International Conference on Image Processing (ICIP), Abu Dhabi, United Arab Emirates.10.1109/ICIP40778.2020.9190878 ↗
6. Abebe, M. (2023). High Dynamic Range Imaging. Fundamentals and Applications of Colour Engineering, Springer.10.1002/9781119827214.ch17 ↗
7. HDR CMOS image sensors for automotive applications10.1109/TED.2022.3164370 ↗
8. HDR image reconstruction from a single exposure using deep CNNs10.1145/3130800.3130816 ↗
9. Le, P., Le, Q., Nguyen, R., and Hua, B. (2023, January 2–7). Single-Image HDR Reconstruction by Multi-Exposure Generation. Proceedings of the 2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Los Alamitos, CA, USA.10.1109/WACV56688.2023.00405 ↗
10. Wang, C., Serrano, A., Pan, X., Chen, B., Myszkowski, K., Seidel, H.P., Theobalt, C., and Leimkühler, T. (2023, January 2–6). Glowgan: Unsupervised learning of hdr images from ldr images in the wild. Proceedings of the IEEE/CVF International Conference on Computer Vision, Paris, France.10.1109/ICCV51070.2023.00964 ↗
11. Dalal, D., Vashishtha, G., Singh, P., and Raman, S. (2023, January 8–11). Single Image LDR to HDR Conversion using Conditional Diffusion. Proceedings of the 2023 IEEE International Conference on Image Processing (ICIP), Kuala Lumpur, Malaysia.10.1109/ICIP49359.2023.10222821 ↗
12. Prabhakar, K.R., Agrawal, S., Singh, D.K., Ashwath, B., and Babu, R.V. (2020, January 23–28). Towards practical and efficient high-resolution HDR deghosting with CNN. Proceedings of the Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK. Proceedings, Part XXI 16.10.1007/978-3-030-58589-1_30 ↗
13. Yan, Q., Gong, D., Shi, Q., Hengel, A.v.d., Shen, C., Reid, I., and Zhang, Y. (2019, January 15–20). Attention-guided network for ghost-free high dynamic range imaging. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00185 ↗
14. The state of the art in HDR deghosting: A survey and evaluation10.1111/cgf.12593 ↗
15. Deep high dynamic range imaging of dynamic scenes10.1145/3072959.3073609 ↗
16. Liu, Z., Lin, W., Li, X., Rao, Q., Jiang, T., Han, M., Fan, H., Sun, J., and Liu, S. (2021, January 20–25). ADNet: Attention-guided Deformable Convolutional Network for High Dynamic Range Imaging. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.10.1109/CVPRW53098.2021.00057 ↗
17. Liu, Z., Wang, Y., Zeng, B., and Liu, S. (2022, January 23–27). Ghost-free high dynamic range imaging with context-aware transformer. Proceedings of the European Conference on Computer Vision, Tel Aviv, Israel.10.1007/978-3-031-19800-7_20 ↗
18. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, Ł., and Polosukhin, I. (2017). Attention is all you need. arXiv.
19. Towards high-quality hdr deghosting with conditional diffusion models10.1109/TCSVT.2023.3326293 ↗
20. Kinoshita, Y., and Kiya, H. (2020, January 7–10). Checkerboard-Artifact-Free Image-Enhancement Network Considering Local and Global Features. Proceedings of the 2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), Auckland, New Zealand.
21. Single image HDR reconstruction using a CNN with masked features and perceptual loss10.1145/3386569.3392403 ↗
22. Khan, Z., Khanna, M., and Raman, S. (2019, January 11–14). FHDR: HDR Image Reconstruction from a Single LDR Image using Feedback Network. Proceedings of the 2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP), Ottawa, ON, Canada.10.1109/GlobalSIP45357.2019.8969167 ↗
23. Deep Reverse Tone Mapping10.1145/3130800.3130834 ↗
24. Ten years of generative adversarial nets (GANs): A survey of the state-of-the-art10.1088/2632-2153/ad1f77 ↗
25. Generative Adversarial Networks10.1145/3422622 ↗
26. Hdr-gan: Hdr image reconstruction from multi-exposed ldr images with large motions10.1109/TIP.2021.3064433 ↗
27. Tel, S., Wu, Z., Zhang, Y., Heyrman, B., Demonceaux, C., Timofte, R., and Ginhac, D. (2023). Alignment-free HDR Deghosting with Semantics Consistent Transformer. arXiv.10.1109/ICCV51070.2023.01179 ↗
28. Diffusion models: A comprehensive survey of methods and applications10.1145/3554729 ↗
29. Deep learning for hdr imaging: State-of-the-art and future trends10.1109/TPAMI.2021.3123686 ↗
30. Kalantari, N.K., and Ramamoorthi, R. (2019). Deep HDR video from sequences with alternating exposures. Computer Graphics Forum, Wiley.10.1111/cgf.13630 ↗
31. Chen, G., Chen, C., Guo, S., Liang, Z., Wong, K.Y.K., and Zhang, L. (2021, January 10–17). HDR Video Reconstruction: A Coarse-to-fine Network and A Real-world Benchmark Dataset. Proceedings of the IEEE/CVF International Conference on Computer Vision, Montreal, QC, Canada.10.1109/ICCV48922.2021.00250 ↗
32. Xu, G., Wang, Y., Gu, J., Xue, T., and Yang, X. (2024, January 16–22). HDRFlow: Real-Time HDR Video Reconstruction with Large Motions. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR52733.2024.02347 ↗
33. Chung, H., and Cho, N.I. (2023, January 2–6). LAN-HDR: Luminance-based Alignment Network for High Dynamic Range Video Reconstruction. Proceedings of the IEEE/CVF International Conference on Computer Vision, Paris, France.10.1109/ICCV51070.2023.01172 ↗
34. Guan, Y., Xu, R., Yao, M., Gao, R., Wang, L., and Xiong, Z. (2024). Diffusion-Promoted HDR Video Reconstruction. arXiv.
35. HDR-VDP-2: A calibrated visual metric for visibility and quality predictions in all luminance conditions10.1145/2010324.1964935 ↗
36. Mantiuk, R.K., Hammou, D., and Hanji, P. (2023). HDR-VDP-3: A multi-metric for predicting image differences, quality and contrast distortions in high dynamic range and regular content. arXiv.
37. Azimi, M., and Mantiuk, R.K. (July, January 29). PU21: A novel perceptually uniform encoding for adapting existing quality metrics for HDR. Proceedings of the 2021 Picture Coding Symposium (PCS), Bristol, UK.10.1109/PCS50896.2021.9477471 ↗
38. Liu, Y., Tian, Y., Wang, S., Zhang, X., and Kwong, S. (2024). Overview of High-Dynamic-Range Image Quality Assessment. J. Imaging, 10.10.20944/preprints202408.0935.v1 ↗
39. ExpandNet: A Deep Convolutional Neural Network for High Dynamic Range Expansion from Low Dynamic Range Content10.1111/cgf.13340 ↗
40. Liu, Y.L., Lai, W.S., Chen, Y.S., Kao, Y.L., Yang, M.H., Chuang, Y.Y., and Huang, J.B. (2020, January 13–19). Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR42600.2020.00172 ↗
41. Chen, X., Liu, Y., Zhang, Z., Qiao, Y., and Dong, C. (2021, January 17–18). HDRUNet: Single Image HDR Reconstruction with Denoising and Dequantization. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, Seattle, WA, USA.10.1109/CVPRW53098.2021.00045 ↗
42. DEUNet: Dual-encoder UNet for simultaneous denoising and reconstruction of single HDR image10.1016/j.cag.2024.01.009 ↗
43. Banterle, F., Ledda, P., Debattista, K., and Chalmers, A. (December, January 29). Inverse tone mapping. Proceedings of the GRAPHITE ’06: Proceedings of the 4th International Conference on Computer Graphics and Interactive Techniques in Australasia and Southeast Asia, Kuala Lumpur, Malaysia.
44. Ronneberger, O., Fischer, P., and Brox, T. (2015, January 5–9). U-Net: Convolutional Networks for Biomedical Image Segmentation. Proceedings of the 18th International Conference, Munich, Germany.10.1007/978-3-319-24574-4_28 ↗
45. Kim, J., Zhu, Z., Bau, T., and Liu, C. (2024, January 17–18). DCDR-UNet: Deformable Convolution Based Detail Restoration via U-shape Network for Single Image HDR Reconstruction. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, Seattle, WA, USA.10.1109/CVPRW63382.2024.00598 ↗
46. DCT-GAN: Dilated convolutional transformer-based GAN for time series anomaly detection10.1109/TKDE.2021.3130234 ↗
47. A unified framework for multi-sensor HDR video reconstruction10.1016/j.image.2013.08.018 ↗
48. Prabhakar, K.R., Arora, R., Swaminathan, A., Singh, K.P., and Babu, R.V. (2019, January 15–17). A fast, scalable, and reliable deghosting method for extreme exposure fusion. Proceedings of the 2019 IEEE International Conference on Computational Photography (ICCP), Tokyo, Japan.10.1109/ICCPHOT.2019.8747329 ↗
49. Lu, Z., Li, J., Liu, H., Huang, C., Zhang, L., and Zeng, T. (2022, January 18–24). Transformer for single image super-resolution. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.10.1109/CVPRW56347.2022.00061 ↗
50. Liu, X., Li, A., Wu, Z., Du, Y., Zhang, L., Zhang, Y., Timofte, R., and Zhu, C. (2024). PASTA: Towards Flexible and Efficient HDR Imaging Via Progressively Aggregated Spatio-Temporal Aligment. arXiv.
51. Diffusion models beat gans on image synthesis
52. Burst photography for high dynamic range and low-light imaging on mobile cameras10.1145/2980179.2980254 ↗
53. Handheld multi-frame super-resolution10.1145/3306346.3323024 ↗
54. Burst Photography for Learning to Enhance Extremely Dark Images10.1109/TIP.2021.3125394 ↗
55. Debevec, P.E., and Malik, J. (2023). Recovering High Dynamic Range Radiance Maps from Photographs. Seminal Graphics Papers: Pushing the Boundaries, Volume 2, Association for Computing Machinery. [1st ed.].10.1145/3596711.3596779 ↗
56. Xu, F., Liu, J., Song, Y., Sun, H., and Wang, X. (2022). Multi-exposure image fusion techniques: A comprehensive review. Remote Sens., 14.10.3390/rs14030771 ↗
57. Ou, Y., Ambalathankandy, P., Ikebe, M., Takamaeda, S., Motomura, M., and Asai, T. (2020). Real-time tone mapping: A state of the art report. arXiv.
58. High dynamic range image tone mapping: Literature review and performance benchmark10.1016/j.dsp.2023.104015 ↗
59. Ward, G. (1994). A contrast-based scalefactor for luminance display. Graphics Gems IV, Academic Press Professional Inc.10.1016/B978-0-12-336156-1.50054-9 ↗
60. Lightness and retinex theory10.1364/JOSA.61.000001 ↗
61. Pattanaik, S.N., Ferwerda, J.A., Fairchild, M.D., and Greenberg, D.P. (1998, January 19–24). A multiscale model of adaptation and spatial vision for realistic image display. Proceedings of the 25th Annual Conference on Computer Graphics and Interactive Techniques, Orlando, FL, USA.10.1145/280814.280922 ↗
62. Reinhard, E., Stark, M., Shirley, P., and Ferwerda, J. (2023). Photographic tone reproduction for digital images. Seminal Graphics Papers: Pushing the Boundaries, Volume 2, Association for Computing Machinery.10.1145/3596711.3596781 ↗
63. Hu, J., Gallo, O., Pulli, K., and Sun, X. (2013, January 23–28). HDR deghosting: How to deal with saturation?. Proceedings of the IEEE conference on computer vision and pattern recognition, Portland, OR, USA.10.1109/CVPR.2013.154 ↗
64. Yoon, H., Uddin, S.M.N., and Jung, Y.J. (2022). Multi-Scale Attention-Guided Non-Local Network for HDR Image Reconstruction. Sensors, 22.10.3390/s22187044 ↗
65. Robust patch-based hdr reconstruction of dynamic scenes10.1145/2366145.2366222 ↗
66. A hybrid CNN for image denoising
67. Enhanced CNN for image denoising10.1049/trit.2018.1054 ↗
68. Beyond a gaussian denoiser: Residual learning of deep cnn for image denoising10.1109/TIP.2017.2662206 ↗
69. Mao, X., Shen, C., and Yang, Y.B. (2016, January 5–10). Image restoration using very deep convolutional encoder-decoder networks with symmetric skip connections. Proceedings of the NIPS’16: Proceedings of the 30th International Conference on Neural Information Processing Systems, Barcelona, Spain.
70. FFDNet: Toward a fast and flexible solution for CNN-based image denoising10.1109/TIP.2018.2839891 ↗
71. He, J., Dong, C., and Qiao, Y. (2019, January 15–20). Modulating image restoration with continual levels via adaptive feature modification layers. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.01131 ↗
72. Deconvolution and Checkerboard Artifacts10.23915/distill.00003 ↗
73. A Decoupled Kernel Prediction Network Guided by Soft Mask for Single Image HDR Reconstruction10.1145/3550277 ↗
74. Dumoulin, V., Belghazi, I., Poole, B., Mastropietro, O., Lamb, A., Arjovsky, M., and Courville, A. (2016). Adversarially Learned Inference. arXiv.
75. A survey on deep learning tools dealing with data scarcity: Definitions, challenges, solutions, tips, and applications10.1186/s40537-023-00727-2 ↗
76. Prabhakar, K.R., and Babu, R.V. (2024, December 12). High Dynamic Range Deghosting Dataset. Available online: https://val.cds.iisc.ac.in/HDR/HDRD/.
77. Funt, B.V., and Shi, L. (2010, January 23–27). The Rehabilitation of MaxRGB. Proceedings of the International Conference on Communications in Computing, Cape Town, South Africa.
78. An Objective Deghosting Quality Metric for HDR Images10.1111/cgf.12818 ↗
79. Nemoto, H., Korshunov, P., Hanhart, P., and Ebrahimi, T. (2015, January 5–6). Visual attention in LDR and HDR images. Proceedings of the 9th International Workshop on Video Processing and Quality Metrics for Consumer Electronics (VPQM), Chandler, AZ, USA.
80. Gardner, M.A., Sunkavalli, K., Yumer, E., Shen, X., Gambaretto, E., Gagné, C., and Lalonde, J.F. (2017). Learning to Predict Indoor Illumination from a Single Image. arXiv.10.1145/3130800.3130891 ↗
81. Chen, X., Li, Z., Zhang, Z., Ren, J.S., Liu, Y., He, J., Qiao, Y., Zhou, J., and Dong, C. (2023). Towards Efficient SDRTV-to-HDRTV by Learning from Image Formation. arXiv.
82. Hanji, P., Mantiuk, R., Eilertsen, G., Hajisharif, S., and Unger, J. (2022, January 7–11). Comparison of single image HDR reconstruction methods—The caveats of quality assessment. Proceedings of the SIGGRAPH ’22: ACM SIGGRAPH 2022 Conference Proceedings, Vancouver, BC, Canada.10.1145/3528233.3530729 ↗
83. Perez-Pellitero, E., Catley-Chandar, S., Leonardis, A., Timofte, R., Wang, X., Li, Y., Wang, T., Song, F., Liu, Z., and Lin, W. (2021, January 19–25). NTIRE 2021 Challenge on High Dynamic Range Imaging: Dataset, Methods and Results. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, Nashville, TN, USA.10.1109/CVPRW53098.2021.00078 ↗
84. Barua, H.B., Stefanov, K., Wong, K., Dhall, A., and Krishnasamy, G. (2024). GTA-HDR: A Large-Scale Synthetic Dataset for HDR Image Reconstruction. arXiv.10.1109/WACV61041.2025.00765 ↗
85. A Multidimensional Choledoch Database and Benchmarks for Cholangiocarcinoma Diagnosis10.1109/ACCESS.2019.2947470 ↗
86. Liu, S., Zhang, X., Sun, L., Liang, Z., Zeng, H., and Zhang, L. (2023, January 17–24). Joint hdr denoising and fusion: A real-world mobile hdr image dataset. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.10.1109/CVPR52729.2023.01342 ↗
87. Consolidated dataset and metrics for high-dynamic-range image quality10.1109/TMM.2021.3076298 ↗
88. Neural Augmentation-Based Saturation Restoration for LDR Images of HDR Scenes10.1109/TIM.2023.3304675 ↗
89. Zhao, F., Liu, Q., and Ikenaga, T. (2023, January 8–11). HDR-LMDA: A Local Area-Based Mixed Data Augmentation Method for Hdr Video Reconstruction. Proceedings of the 2023 IEEE International Conference on Image Processing (ICIP), Kuala Lumpur, Malaysia.10.1109/ICIP49359.2023.10222677 ↗
90. Richter, T. (2013, January 8–11). On the standardization of the JPEG XT image compression. Proceedings of the 2013 Picture Coding Symposium (PCS), San Jose, CA, USA.10.1109/PCS.2013.6737677 ↗
91. Optimizing a tone curve for backward-compatible high dynamic range image and video compression
92. Performance evaluation of objective quality metrics for HDR image compression
93. An extensive performance evaluation of full-reference HDR image quality metrics10.1007/s41233-017-0007-4 ↗
94. Benchmarking of objective quality metrics for HDR image quality assessment10.1186/s13640-015-0091-4 ↗
95. FovVideoVDP: A visible difference predictor for wide field-of-view video10.1145/3450626.3459831 ↗
96. HDR-VQM: An objective quality measure for high dynamic range video10.1016/j.image.2015.04.009 ↗
97. No-reference image quality assessment in the spatial domain10.1109/TIP.2012.2214050 ↗
98. Making a “completely blind” image quality analyzer10.1109/LSP.2012.2227726 ↗
99. Mantiuk, R., Daly, S., and Kerofsky, L. (2008). Display adaptive tone mapping. ACM SIGGRAPH 2008 Papers, ACM.10.1145/1399504.1360667 ↗
100. NIMA: Neural image assessment10.1109/TIP.2018.2831899 ↗