In low-light environments, the signal-to-noise ratio (SNR) of complementary metal-oxide-semiconductor (CMOS) image sensors decreases significantly. In order to improve the imaging quality, this paper proposes a transformer-based denoising method, illumination prompting dual-attention transformer (IPDT). In the noise model, the effect of dark current noise on the low light images is emphasized. The denoising network contains the dual-attention transformer block (DTB) module including spatial-channel attention and the prompt-block (PB). The DTB captures global and detail information of low-light images through cross-window and cross-channel interactions, respectively. The PB acquires illumination information through learnable prompt parameters, dynamically guiding the denoising network. Experiments on see-in-the-dark (SID) dataset and smartphone image denoising dataset (SIDD) indicate that the proposed method effectively suppresses the noise of low-light images and demonstrates superior performance in terms of blind referenceless image spatial quality evaluator (BRISQUE) and multi-scale structural similarity index (MS-SSIM) metrics.
| [1] |
LEKTINEN J. Noise2Noise: learning image restoration without clean data[EB/OL]. (2018-03-12) [2025-09-30]. http://arxiv.org/abs/1803.04189.
|
| [2] |
Mansour Y, Heckel R. Zero-Shot Noise2Noise: efficient image denoising without any data. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 18–24, 2023, Vancouver, Canada, 2023, New York: IEEE, 14018-14027[C]
|
| [3] |
Nan Y, Zhen W, Jun Z, et al. Unsupervised model-driven neural network based image denoising for transmission line monitoring. Optoelectronics letters, 2023, 194248251. J]
|
| [4] |
Zhang K, Zuo W, Chen Y, et al. Beyond a Gaussian denoiser: residual learning of deep CNN for image denoising. IEEE transactions on image processing, 2017, 26731423155. J]
|
| [5] |
Wei K, Fu Y, Yang J, et al. A physics-based noise formation model for extreme low-light raw denoising. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 14–19, 2020, Seattle, USA, 2020, New York: IEEE, 2755-2764[C]
|
| [6] |
Zhang Y, Qin H, Wang X, et al. Rethinking noise synthesis and modeling in raw denoising. Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, October 11–17, 2021, Montreal, Canada, 2021, New York: IEEE, 4573-4581[C]
|
| [7] |
Chen J, Chen J, Chao H, et al. Image blind denoising with generative adversarial network based noise modeling. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, June 18–22, 2018, Salt Lake City, USA, 2018, New York: IEEE, 3155-3164[C]
|
| [8] |
Li Y, Li J, Xiong Z. Look-up table compression for efficient image restoration. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 16–22, 2024, Seattle, USA, 2024, New York: IEEE, 26016-26025[C]
|
| [9] |
Liu G, Ding Y, Li M, et al. Reconstructed convolution module based look-up tables for efficient image super-resolution. Proceedings of the IEEE/CVF International Conference on Computer Vision, October 1–5, 2023, Paris, France, 2023, New York: IEEE, 12217-12226[C]
|
| [10] |
YANG S, HUANG B, ZHANG Y, et al. DnLUT: ultra-efficient color image denoising via channel-aware lookup tables[EB/OL]. (2025-03-20) [2025-09-30]. http://arxiv.org/abs/2503.15931.
|
| [11] |
GU A, DAO T. Mamba: linear-time sequence modeling with selective state spaces[EB/OL]. (2023-12-01) [2025-09-30]. http://arxiv.org/abs/2312.00752.
|
| [12] |
LI B, ZHAO H, WANG W, etal. MaIR: a locality and continuity-preserving mamba for image restoration[EB/OL]. (2024-12-28) [2025-09-30]. http://arxiv.org/abs/2412.20066.
|
| [13] |
Gow R D, Renshaw D, Findlater K, et al. A comprehensive tool for modeling CMOS image-sensor-noise performance. IEEE transactions on electron devices, 2007, 54613211329. J]
|
| [14] |
KONNIK M, WELSH J. High-level numerical simulations of noise in CCD and CMOS photosensors: review and tutorial[EB/OL]. (2014-12-11) [2025-09-30]. http://arxiv.org/abs/1412.4031.
|
| [15] |
Leyris C, Hoffmann A, Valenza M, et al. Trap competition inducing R.T.S noise in saturation range in N-MOSFETs. Proceedings of Noise in Devices and Circuits III, May 23–25, 2005, Austin, Texas, USA, 2005, Bellingham: SPIE, 41-51[C]
|
| [16] |
VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[J]. Advances in neural information processing systems, 2017, 30.
|
| [17] |
Ronneberger O, Fischer P, Brox T. U-Net: convolutional networks for biomedical image segmentation. Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, October 5–9, 2015, Munich, Germany, 2015, Cham: Springer International Publishing, 234-241[C]
|
| [18] |
Liu Z, Lin Y, Cao Y, et al. Swin transformer: hierarchical vision transformer using shifted windows. Proceedings of the IEEE/CVF International Conference on Computer Vision, October 11–17, 2021, Montreal, Canada, 2021, New York: IEEE, 10012-10022[C]
|
| [19] |
Chen C, Chen Q, Xu J, et al. Learning to see in the dark. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, June 18–22, 2018, Salt Lake City, USA, 2018, New York: IEEE, 3291-3300[C]
|
| [20] |
Abdelhamed A, Lin S, Brown M S. A high-quality denoising dataset for smartphone cameras. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, June 18–22, 2018, Salt Lake City, USA, 2018, New York: IEEE, 1692-1700[C]
|
| [21] |
Dabov K, Foi A, Katkovnik V, et al. Color image denoising via sparse 3D collaborative filtering with grouping constraint in luminance-chrominance space. Proceedings of the 2007 IEEE International Conference on Image Processing, September 16–19, 2007, San Antonio, TX, USA, 2007, New York: IEEE, I-313–I-316[C]
|
| [22] |
Zhang K, Li Y, Zuo W, et al. Plug-and-play image restoration with deep denoiser prior. IEEE transactions on pattern analysis and machine intelligence, 2022, 441063606376. J]
|
| [23] |
Liang J, Cao J, Sun G, et al. SwinIR: image restoration using swin transformer. Proceedings of the IEEE/CVF International Conference on Computer Vision, October 11–17, 2021, Montreal, Canada, 2021, New York: IEEE, 1833-1844[C]
|
| [24] |
Mittal A, Moorthy A K, Bovik A C. No-reference image quality assessment in the spatial domain. IEEE transactions on image processing, 2012, 211246951708. J]
|
| [25] |
Wang Z, Simoncelli E P, Bovik A C. Multiscale structural similarity for image quality assessment. Proceedings of the 37th Asilomar Conference on Signals, Systems & Computers, November 9–12, 2003, Pacific Grove, CA, USA, 2003, New York: IEEE, 1398-1402[C]
|
Rights & permissions
Tianjin University of Technology
PDF
