Abstract
In the absence of well-exposed contents in images, high dynamic range image (HDRI) provides an attractive option that fuses stacked low dynamic range (LDR) images into an HDR image. Existing HDRI methods utilized convolutional neural networks (CNNs) to model local correlations, which can perform well on LDR images with static scenes, but always failed on dynamic scenes where large motions exist. Here we focus on the dynamic scenarios in HDRI, and propose a Query-based Transformer framework, called Q-TrHDRI. To avoid ghosting artifacts induced by moving content fusion, Q-TrHDRI uses Transformer instead of CNNs for feature enhancement and fusion, allowing global interactions across different LDR images. To further improve performance, we investigate comprehensively different strategies of transformers and propose a query-attention scheme for finding related contents across LDR images and a linear fusion scheme for skillfully borrowing complementary contents from LDR images. All these efforts make Q-TrHDRI a simple yet solid transformer-based HDRI baseline. The thorough experiments also validate the effectiveness of the proposed Q-TrHDRI, where it achieves superior performances over state-of-the-art methods on various challenging datasets.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Alexey, D., et al.: An image is worth 16 \(\times \)16 words: transformers for image recognition at scale. In: ICLR (2019)
Chen, H., et al.: Pre-trained image processing transformer. In: CVPR, pp. 12299–12310, June 2021
Chi, Y., Zhang, X., Chan, S.H.: HDR imaging with spatially varying signal-to-noise ratios. In: CVPR, pp. 5724–5734, June 2023
Hassani, A., Walton, S., Shah, N., Abuduweili, A., Li, J., Shi, H.: Escaping the big data paradigm with compact transformers. arXiv:2104.05704 (2021)
Kalantari, N.K., Ramamoorthi, R.: Deep high dynamic range imaging of dynamic scenes. ACM TOG 36(4), 144 (2017)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)
Lee, C., Li, Y., Monga, V.: Ghost-free high dynamic range imaging via rank minimization. IEEE SPL 21(9), 1045–1049 (2014)
Liang, J., Cao, J., Sun, G., Zhang, K., Van Gool, L., Timofte, R.: SwinIR: image restoration using Swin transformer. In: ICCVW (2021)
Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: ICCV, pp. 10012–10022 (2021)
Niu, Y., Wu, J., Liu, W., Guo, W., Lau, R.W.H.: HDR-GAN: HDR image reconstruction from multi-exposed LDR images with large motions. IEEE TIP 30, 3885–3896 (2021)
Oh, T., Lee, J., Tai, Y., Kweon, I.S.: Robust high dynamic range imaging by rank minimization. IEEE TPAMI 37(6), 1219–1232 (2015)
Pan, Z., Zhuang, B., Liu, J., He, H., Cai, J.: Scalable vision transformers with hierarchical pooling. In: ICCV, pp. 377–386, October 2021
Prabhakar, K.R., Senthil, G., Agrawal, S., Babu, R.V., Gorthi, R.K.S.S.: Labeled from unlabeled: exploiting unlabeled data for few-shot deep HDR deghosting. In: CVPR, pp. 4875–4885 (2021)
Qu, L., Liu, S., Wang, M., Song, Z.: Transmef: a transformer-based multi-exposure image fusion framework using self-supervised multi-task learning. In: AAAI (2022)
Sen, P., Kalantari, N.K., Yaesoubi, M., Darabi, S., Goldman, D.B., Shechtman, E.: Robust patch-based HDR reconstruction of dynamic scenes. ACM TOG 31(6), 203 (2012)
Tursun, O.T., Akyüz, A.O., Erdem, A., Erdem, E.: An objective deghosting quality metric for HDR images. In: Eurographics, pp. 139–152 (2016)
Vaswani, A., et al.: Attention is all you need. In: NeurIPS, vol. 30 (2017)
Wu, G., Zheng, W.S., Lu, Y., Tian, Q.: PSLT: a light-weight vision transformer with ladder self-attention and progressive shift. IEEE TPAMI, pp. 1–16 (2023)
Wu, S., Xu, J., Tai, Y.-W., Tang, C.-K.: Deep high dynamic range imaging with large foreground motions. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11206, pp. 120–135. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01216-8_8
Xu, H., Ma, J., Zhang, X.: MEF-GAN: multi-exposure image fusion via generative adversarial networks. IEEE TIP 29, 7203–7216 (2020)
Yan, Q., et al.: Attention-guided network for ghost-free high dynamic range imaging. In: CVPR, pp. 1751–1760 (2019)
Yan, Q., et al.: Deep HDR imaging via a non-local network. IEEE TIP 29, 4308–4322 (2020)
Yoon, H., Uddin, S.M.N., Jung, Y.J.: Multi-scale attention-guided non-local network for HDR image reconstruction. Sensors 22(18), 7044 (2022)
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Chen, B., Yin, JL., Chen, BH., Liu, X. (2024). Q-TrHDRI: A Qurey-Based Transformer for High Dynamic Range Imaging with Dynamic Scenes. In: Liu, Q., et al. Pattern Recognition and Computer Vision. PRCV 2023. Lecture Notes in Computer Science, vol 14435. Springer, Singapore. https://doi.org/10.1007/978-981-99-8552-4_24
Download citation
DOI: https://doi.org/10.1007/978-981-99-8552-4_24
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-8551-7
Online ISBN: 978-981-99-8552-4
eBook Packages: Computer ScienceComputer Science (R0)