A Novel Solution for Reconstructing More Details High Dynamic Range Image
Source abstract
Abstract
Although scholars have made significant progress in obtaining high dynamic range (HDR) images by using deep learning algorithms to fuse multiple exposure images, there are still challenges, such as image artifacts and distortion in high-brightness and low-brightness saturated areas. To this end, we propose a more detailed high dynamic range (MDHDR) method. Firstly, our proposed method uses super-resolution to enhance the details of long-exposure and short-exposure images and fuses them into medium-exposure images, respectively. Then, the HDR image is reconstructed by fusing the original medium-exposure, enhanced medium-exposure images. Extensive experimental results show that the proposed method can reconstruct good HDR images that perform better image clarity in quantitative tests and improve HDR-VDP2 by 4.8% in qualitative tests.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Image Processing Techniques · Advanced Vision and Imaging · Image and Signal Denoising Methods
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Institute of Electrical and Control Engineering, National Yang Ming Chiao Tung University, No. 1001, Daxue Rd. East Dist., Hsinchu City 300093, Taiwan
References (51)
Show source-provided references
1. Guo, C., and Jiang, X. (2022, January 4–8). Lhdr: Hdr reconstruction for legacy content using a lightweight dnn. Proceedings of the Asian Conference on Computer Vision, Macau SAR, China.10.1007/978-3-031-26313-2_19 ↗
2. Bogoni, L. (2000, January 3–7). Extending dynamic range of monochrome and color images through fusion. Proceedings of the 15th International Conference on Pattern Recognition, ICPR-2000, Barcelona, Spain.10.1109/ICPR.2000.903475 ↗
3. High dynamic range video10.1145/882262.882270 ↗
4. Tomaszewska, A., and Mantiuk, R. (2025, February 02). Image Registration for Multi-Exposure High Dynamic Range Image Acquisition. Available online: https://scispace.com/pdf/image-registration-for-multi-exposure-high-dynamic-range-4tym59cxpm.pdf.
5. Ghost-free high dynamic range imaging via rank minimization10.1109/LSP.2014.2323404 ↗
6. Robust high dynamic range imaging by rank minimization10.1109/TPAMI.2014.2361338 ↗
7. Gradient-Directed Multiexposure Composition10.1109/TIP.2011.2170079 ↗
8. Robust patch-based hdr reconstruction of dynamic scenes10.1145/2366145.2366222 ↗
9. 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 ↗
10. Deep high dynamic range imaging of dynamic scenes10.1145/3072959.3073609 ↗
11. Wu, S., Xu, J., Tai, Y.-W., and Tang, C.-K. (2018, January 8–14). Deep high dynamic range imaging with large foreground motions. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.10.1007/978-3-030-01216-8_8 ↗
12. Yan, Q., Gong, D., Shi, Q., van den Hengel, A., 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 ↗
13. Deep HDR imaging via a non-local network10.1109/TIP.2020.2971346 ↗
14. Hdr-gan: Hdr image reconstruction from multi-exposed ldr images with large motions10.1109/TIP.2021.3064433 ↗
15. Ye, Q., Xiao, J., Lam, K.-m., and Okatani, T. (2021, January 20–24). Progressive and selective fusion network for high dynamic range imaging. Proceedings of the 29th ACM International Conference on Multimedia, Chengdu, China.10.1145/3474085.3475651 ↗
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. HDR light field imaging of dynamic scenes: A learning-based method and a benchmark dataset10.1016/j.patcog.2024.110313 ↗
18. Guan, Y., Xu, R., Yao, M., Huang, J., and Xiong, Z. (2024). EdiTor: Edge-guided transformer for ghost-free high dynamic range imaging. ACM Trans. Multimed. Comput. Commun. Appl.10.1145/3657293 ↗
19. Hu, T., Yan, Q., Qi, Y., and Zhang, Y. (2024, January 17–21). Generating content for hdr deghosting from frequency view. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR52733.2024.02431 ↗
20. Single-image HDR reconstruction assisted ghost suppression and detail preservation network for multi-exposure HDR imaging10.1109/TCI.2024.3369396 ↗
21. HDRfeat: A feature-rich network for high dynamic range image reconstruction10.1016/j.patrec.2024.06.019 ↗
22. Image super-resolution using deep convolutional networks10.1109/TPAMI.2015.2439281 ↗
23. Kim, J., Lee, J.K., and Lee, K.M. (2016, January 26–30). Accurate image super-resolution using very deep convolutional networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.182 ↗
24. Shi, W., Caballero, J., Huszár, F., Totz, J., Aitken, A.P., Bishop, R., Rueckert, D., and Wang, Z. (2016, January 27–30). Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.207 ↗
25. Wang, X., Yu, K., Wu, S., Gu, J., Liu, Y., Dong, C., Qiao, Y., and Change Loy, C. (2018, January 8–14). Esrgan: Enhanced super-resolution generative adversarial networks. Proceedings of the European Conference on Computer Vision (ECCV) Workshops, Munich, Germany.10.1007/978-3-030-11021-5_5 ↗
26. Zhang, Y., Tian, Y., Kong, Y., Zhong, B., and Fu, Y. (2018, January 18–23). Residual dense network for image super-resolution. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00262 ↗
27. Qiu, Y., Wang, R., Tao, D., and Cheng, J. (2019, January 27–28). Embedded block residual network: A recursive restoration model for single-image super-resolution. Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, Republic of Korea.10.1109/ICCV.2019.00428 ↗
28. Wang, X., Xie, L., Dong, C., and Shan, Y. (2021, January 11–17). Real-esrgan: Training real-world blind super-resolution with pure synthetic data. Proceedings of the IEEE/CVF International Conference on Computer Vision, Montreal, BC, Canada.10.1109/ICCVW54120.2021.00217 ↗
29. Ayazoglu, M. (2021, January 20–25). Extremely lightweight quantization robust real-time single-image super resolution for mobile devices. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.10.1109/CVPRW53098.2021.00280 ↗
30. Ronneberger, O., Fischer, P., and Brox, T. (2015, January 5–9). U-net: Convolutional networks for biomedical image segmentation. Proceedings of the Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany. Proceedings, Part III.10.1007/978-3-319-24574-4_28 ↗
31. Johnson, J., Alahi, A., and Fei-Fei, L. (2016, January 11–14). Perceptual losses for real-time style transfer and super-resolution. Proceedings of the Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands. Proceedings, Part II.10.1007/978-3-319-46475-6_43 ↗
32. Exposure-structure blending network for high dynamic range imaging of dynamic scenes10.1109/ACCESS.2020.3005022 ↗
33. Yang, K., Hu, T., Dai, K., Chen, G., Cao, Y., Dong, W., Wu, P., Zhang, Y., and Yan, Q. (2024, January 17–18). CRNet: A Detail-Preserving Network for Unified Image Restoration and Enhancement Task. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, Seattle, WA, USA.10.1109/CVPRW63382.2024.00615 ↗
34. Ledig, C., Theis, L., Huszár, F., Caballero, J., Cunningham, A., Acosta, A., Aitken, A., Tejani, A., Totz, J., and Wang, Z. (2017, January 21–26). Photo-realistic single image super-resolution using a generative adversarial network. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.19 ↗
35. Karaimer, H.C., and Brown, M.S. (2016, January 11–14). A software platform for manipulating the camera imaging pipeline. Proceedings of the Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands. Proceedings, Part I.10.1007/978-3-319-46448-0_26 ↗
36. 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/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR42600.2020.00172 ↗
37. Color image processing pipeline10.1109/MSP.2005.1407713 ↗
38. Tursun, O.T., Akyüz, A.O., Erdem, A., and Erdem, E. (2016). An objective deghosting quality metric for HDR images. Computer Graphics Forum, Wiley Online Library.10.1111/cgf.12818 ↗
39. (2025, March 23). Try Photomatix Pro. Available online: https://www.hdrsoft.com/download/photomatix-pro.html.
40. Boitard, R., Pourazad, M.T., and Nasiopoulos, P. (2016, January 4–6). High dynamic range versus standard dynamic range compression efficiency. Proceedings of the 2016 Digital Media Industry & Academic Forum (DMIAF), Santorini, Greece.10.1109/DMIAF.2016.7574890 ↗
41. (2002). Recommendation, Parameter Values for the HDTV Standards for Production and International Programme Exchange (Standard No. BT.709-6 (06/2015)).
42. (2012). Parameter Values for Ultra-High Definition Television Systems for Production and International Programme Exchange (Standard No. ITU-R BT.2020-1 (06/2014)). ITU-T, Bt. 2020.
43. 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.
44. Prabhakar, K.R., Arora, R., Swaminathan, A., Singh, K.P., and Babu, R.V. (2019, January 5–17). 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 ↗
45. Pérez-Pellitero, E., Catley-Chandar, S., Leonardis, A., and Timofte, R. (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, Nashville, TN, USA.
46. Yang, X., Xu, K., Song, Y., Zhang, Q., Wei, X., and Lau, R.W. (2018, January 18–23). Image correction via deep reciprocating HDR transformation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00193 ↗
47. Vasu, S., Shenoi, A., and Rajagopazan, A. (2018, January 7–10). Joint hdr and super-resolution imaging in motion blur. Proceedings of the 2018 25th IEEE International Conference on Image Processing (ICIP), Athens, Greece.10.1109/ICIP.2018.8451735 ↗
48. Learning HDR video reconstruction for dual-exposure sensors with temporally-alternating exposures10.1016/j.cag.2022.04.008 ↗
49. Kim, J., and Kim, M.H. (2023, January 2–3). Joint demosaicing and deghosting of time-varying exposures for single-shot hdr imaging. Proceedings of the IEEE/CVF International Conference on Computer Vision, Paris, France.10.1109/ICCV51070.2023.01129 ↗
50. Conde, M.V., Vasluianu, F., Vazquez-Corral, J., and Timofte, R. (2023, January 2–7). Perceptual image enhancement for smartphone real-time applications. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, Waikoloa, HI, USA.10.1109/WACV56688.2023.00189 ↗
51. HDR-VDP-2: A calibrated visual metric for visibility and quality predictions in all luminance conditions10.1145/2010324.1964935 ↗