HWT-SRNet：异质窗口图像超分辨率重建网络

卢迪; 党安圆

doi:10.11999/JEIT250868

HWT-SRNet：异质窗口图像超分辨率重建网络

doi: 10.11999/JEIT250868 cstr: 32379.14.JEIT250868

卢迪^{1, 2, ,},
党安圆^{1, 2}

1.
哈尔滨理工大学测控技术与通信工程学院哈尔滨 150080
2.
哈尔滨理工大学模式识别与信息感知黑龙江省重点实验室哈尔滨 150080

详细信息

作者简介:
卢迪：女，教授，博士，研究方向为数据融合、图像处理等

党安圆：男，硕士生，研究方向为图像处理、超分辨率重建等

通讯作者:
卢迪　ludizeng@hrbust.edu.cn

中图分类号: TN911.73
计量
- 文章访问数: 61
- HTML全文浏览量: 29
- PDF下载量: 12
- 被引次数: 0
出版历程
- 收稿日期: 2025-09-04
- 修回日期: 2026-05-29
- 录用日期: 2026-05-29
- 网络出版日期: 2026-06-08

HWT-SRNet: Heterogeneous Windows Transformer Network for Image Super-Resolution

LU Di^{1, 2
, ,},
DANG Anyuan^{1, 2}

1.
School of Measurement and Control Technology and Communication Engineering, Harbin University of Science and Technology, Harbin 150080, China
2.
Heilongjiang Province Key Laboratory of Pattern Recognition and Information Perception, Harbin University of Science and Technology, Harbin 150080, China

摘要

摘要: 在大数据时代，图像质量参差不齐，对低质量图像进行高分辨率重建具有重要的研究与应用价值。基于 Transformer的单图像超分辨率方法通常将自注意力机制限制在局部非重叠窗口中，导致感受野受限、窗口边界失真以及高频细节重构能力不足等问题。为此，该文提出一种基于Swin IR的异质窗口注意力网络(Heterogeneous Window Transformer Network for Image Super-Resolution, HWT-SRNet)。首先，设计异质窗口注意力机制，充分融合多尺度特征，以缓解窗口边界失真问题并有效扩大感受野。其次，针对Transformer在高频信息重构能力上的不足，提出一种高频先验特征提取网络，增强网络对边缘与纹理细节的恢复能力。实验结果表明，HWT-SRNet在Set5, Set14, BSD100, Urban100, Manga109五个基准测试集上，PSNR指标相比基线模型Swin IR提升0.10～0.37 dB，同时，与其他具有代表性的超分模型CAT, ACT, ART等相比，在图像细节和纹理方面也取得了更优的视觉效果。
- 超分辨率重建 /
- Transformer /
- 异质窗口 /
- 高频先验
Abstract: In the era of big data, image quality varies greatly. Reconstructing high-resolution images from low-quality inputs is therefore an important task in computer vision. Existing super-resolution methods based on window self-attention, such as SwinIR, have limited receptive fields and insufficient ability to capture high-frequency details. These limitations weaken the reconstruction of fine image structures. To address these issues, this study proposes the Heterogeneous Windows Transformer Network for Image Super-Resolution (HWT-SRNet), a new architecture built on SwinIR. Through targeted module design, HWT-SRNet improves high-frequency detail extraction while expanding the receptive field, providing an effective solution for image super-resolution. Methods Based on SwinIR, this study designs two key modules to improve super-resolution reconstruction. First, the Residual Heterogeneous Windows Transformer Block (RHWTB) alternates square windows and pale-shaped windows. This design preserves local feature extraction while expanding the receptive field, enabling the network to model both fine-grained details and global structural information. The window size and alternation frequency are optimized to balance computational efficiency and feature extraction. Second, the High-Frequency Prior Feature Extraction Network (HFPFEN) is used to compensate for the limited high-frequency modeling ability of Transformer-based super-resolution models. HFPFEN extracts high-frequency prior information from images using a Difference of Gaussians (DoG) filter. The DoG filter emphasizes edges and textures by computing the difference between lightly and heavily blurred images. The extracted high-frequency information is then fused with the heterogeneous window attention mechanism. This design allows HWT-SRNet to enhance fine details while maintaining structural coherence. Because the DoG filter is applied in the spatial domain, the model can capture and reconstruct sharp edges and textures without frequency-domain transformation. Results and Discussions Experiments are conducted on five widely used benchmark datasets: Set5, Set14, BSD100, Urban100, and Manga109. HWT-SRNet is compared with representative advanced methods, including ACT, ART, and CAT. The results show superior performance across key evaluation metrics (Table 1). Compared with baseline models, HWT-SRNet improves the Peak Signal-to-Noise Ratio (PSNR) by 0.10 dB to 0.37 dB, confirming its effect in improving image quality. The Structural Similarity Index Measure (SSIM) also shows consistent improvement, indicating better perceptual quality and more accurate reconstruction. Qualitative results further show that HWT-SRNet restores sharper edges, preserves textures more effectively, and reduces blurring artifacts. Ablation studies are conducted to evaluate the contributions of RHWTB and HFPFEN (Table 2). The results confirm that heterogeneous window attention and high-frequency prior extraction jointly improve local feature refinement and global context modeling. Therefore, HWT-SRNet provides an efficient solution for receptive field expansion and high-frequency detail reconstruction. Conclusion This paper proposes HWT-SRNet to address the limited receptive fields and insufficient high-frequency detail capture of existing super-resolution algorithms. By integrating heterogeneous window attention with high-frequency prior feature extraction, the model achieves more effective fusion of local and global features. Experimental results confirm that HWT-SRNet improves both PSNR and SSIM and outperforms representative advanced methods. However, this study does not specifically examine the model’s adaptability to noise interference in real-world scenarios. Future research can further improve the robustness of HWT-SRNet to noisy and degraded inputs and evaluate its generalization on specialized datasets, such as medical and satellite images.
- Super-resolution reconstruction /
- Transformer /
- Heterogeneous windows /
- High-frequency prior

HTML全文

图 1 不同的注意力机制

下载: 全尺寸图片幻灯片

图 2 异质窗口图像超分辨率重建网络

下载: 全尺寸图片幻灯片

图 3 异质窗口注意力模块

下载: 全尺寸图片幻灯片

图 4 高频先验提取网络

下载: 全尺寸图片幻灯片

图 5 不同方法在Set14数据集的图像4倍超分辨率重构比较

下载: 全尺寸图片幻灯片

图 6 不同方法在Urban100数据集的图像4倍超分辨率重构比较

下载: 全尺寸图片幻灯片

图 7 不同模块在Set5数据集“baby”图像4倍超分辨率重构视觉效果比较

下载: 全尺寸图片幻灯片

表 1 不同方法各数据集的PSNR和SSIM均值比较

算法	缩放因子	Set5	Set14	BSD100	Urban100	Manga109
算法	缩放因子	PSNR/SSIM/	PSNR/SSIM	PSNR/SSIM	PSNR/SSIM	PSNR/SSIM
ESWT^[8]	×2	38.33/0.9615	34.22/0.9233	32.47/0.9034	33.27/0.9397	39.79/0.9790
CAT-R^[7]		38.48/0.9625	34.53/0.9251	32.56/0.9045	34.08/0.9443	40.09/0.9804
Swin IR^[6]		38.42/0.9623	34.46/0.9250	32.53/0.9041	33.81/0.9427	39.92/0.9797
ACT^[14]		38.46/0.9626	34.60/0.9256	32.56/0.9048	34.07/0.9443	39.95/0.9804
CRAFT^[18]		38.23/0.9615	33.92/0.9211	32.33/0.9016	32.86/0.9343	39.39/0.9786
ART^[11]		38.56/0.9629	34.59/0.9267	32.58/0.9048	34.30/0.9452	40.24/0.9808
DFDN^[20]		38.19/0.9612	33.85/0.9199	32.30/0.9013	32.68/0.9335	——
MDIESR^[21]		38.17/0.9613	33.83/0.9200	32.31/0.9013	32.65/0.9331	——
HWT-SRNet		38.59/0.9632	34.81/0.9287	32.58/0.9050	34.42/0.9453	40.25/0.9812
ESWT^[8]	×3	34.63/0.9290	30.55/0.8464	29.23/0.8088	28.70/0.8628	34.05/0.9479
CAT-R^[7]		34.99/0.9320	31.00/0.8539	29.49/0.8154	29.91/0.8848	35.29/0.9542
Swin IR^[6]		34.97/0.9318	30.93/0.8534	29.46/0.8145	29.75/0.8826	35.12/0.9537
ACT^[14]		35.03/0.9321	31.08/0.8541	29.51/0.8164	30.08/0.8858	35.27/0.954
CRAFT^[18]		34.71/0.9295	30.61/0.8469	29.24/0.8093	28.77/0.8635	34.29/0.9491
ART^[11]		35.07/0.9325	31.02/0.8541	29.51/0.8159	30.10/0.8871	35.39/0.9548
DFDN^[20]		34.69/0.9293	30.55/0.8464	29.25/0.8089	28.70/0.8630	——
MDIESR^[21]		34.69/0.9295	30.58/0.8465	29.25/0.8087	28.72/0.8634	——
HWT-SRNet		35.12/0.9344	31.06/0.8551	29.57/0.8173	30.18/0.8889	35.48/0.9552
ESWT^[8]	×4	32.46/0.8979	28.80/0.7866	27.70/0.7410	26.56/0.8006	30.94/0.9136
CAT-R^[7]		32.89/0.9044	29.13/0.7955	27.95/0.7500	27.62/0.8292	32.16/0.9269
Swin IR^[6]		32.92/0.9044	29.09/0.7950	27.92/0.7489	27.45/0.8254	32.03/0.9260
ACT^[14]		32.97/0.9031	29.18/0.7954	27.95/0.7507	27.74/0.8305	32.20/0.9267
CRAFT^[18]		32.52/0.8989	28.85/0.7872	27.72/0.7418	26.56/0.7995	31.18/0.9168
ART^[11]		33.04/0.9051	29.16/0.7958	27.97/0.7510	27.77/0.8321	32.31/0.9283
DFDN^[20]		32.56/0.8989	28.87/0.7880	27.73/0.7414	26.59/0.8008	——
MDIESR^[21]		32.49/0.8986	28.84/0.7867	27.73/0.7399	26.59/0.8007	——
HWT-SRNet		33.08/0.9060	29.23/0.7975	28.02/0.7520	27.82/0.8370	32.35/0.9296

下载: 导出CSV

表 2 不同方法各数据集的LPIPS均值比较(×4)

算法	Set5	Set14	BSD100	Urban100	Manga109
ESWT^[8]	0.2078	0.2977	0.3383	0.2812	0.1912
CAT-R^[7]	0.2061	0.2927	0.3279	0.2496	0.1819
Swin IR^[6]	0.2079	0.2957	0.3321	0.2602	0.1847
ACT^[14]	0.2078	0.2904	0.3235	0.2506	0.1840
CRAFT^[18]	0.2136	0.3044	0.3389	0.2816	0.1920
ART^[11]	0.2068	0.2913	0.3259	0.2464	0.1804
HWT-SRNet	0.2050	0.2907	0.3255	0.2448	0.1799

下载: 导出CSV

表 3 参数量与重构时间的比较

算法	参数量	重构时间(s)
ESWT^[8]	589 k	1.20
CAT-R^[7]	16.6 M	4.41
Swin IR^[6]	11.9 M	1.38
ACT^[14]	46 M	10.51
CRAFT^[18]	753 k	1.92
ART^[11]	16.55 M	3.85
HWT-SRNet	16.63 M	2.96

下载: 导出CSV

表 4 不同窗口大小对比实验结果

序号	窗口形状	窗口大小	Multi-adds(GMac)	PSNR/SSIM
1	方形窗口	(8,8)	53.6	32.92/0.9044
		(16,16)	63.8	32.98/0.9050
		(32,32)	119.3	33.01/0.9051
2	栅栏形窗口	2	79.5	32.56/0.8989
		4	82.4	32.82/0.9029
		8	94.1	32.99/0.9049
		16	120.3	33.01/0.9050
3	异质窗口	(8,8),8	81.4	33.00/0.9050
		(8,8),16	87.5	33.01/0.9052
		(16,16),4	73.1	32.90/0.9040
		(16,16),8	87.0	33.03/0.9054

下载: 导出CSV

表 5 不同模块对比实验结果

序号	Swin IR	异质窗口	高频先验特征提取网络	PSNR/SSIM
1	√	×	×	32.92/0.9044
2	√	√	×	33.03/0.9054
3	√	×	√	32.98/0.9049
4	√	√	√	33.08/0.9060

下载: 导出CSV

参考文献(23)

[1]	DONG Chao, LOY C C, HE Kaiming, et al. Learning a deep convolutional network for image super-resolution[C]. The 13th European Conference on Computer Vision, Zurich, Switzerland, 2014: 184–199. doi: 10.1007/978-3-319-10593-2_13.
[2]	DONG Chao, LOY C C, and TANG Xiaoou. Accelerating the super-resolution convolutional neural network[C]. 14th European Conference on Computer Vision, Amsterdam, The Netherlands, 2016: 391–407. doi: 10.1007/978-3-319-46475-6_25.
[3]	ZHANG Yulun, LI Kunpeng, LI Kai, et al. Image super-resolution using very deep residual channel attention networks[C]. The 15th European Conference on Computer Vision, Munich, Germany, 2018: 294–310. doi: 10.1007/978-3-030-01234-2_18.
[4]	DOSOVITSKIY A, BEYER L, KOLESNIKOV A, et al. An image is worth 16x16 words: Transformers for image recognition at scale[C]. The 9th International Conference on Learning Representations, Vienna, Austria, 2021: 1–21.
[5]	LIU Ze, LIN Yutong, CAO Yue, et al. Swin transformer: Hierarchical vision transformer using shifted windows[C]. The 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, Canada, 2021: 9992–10002. doi: 10.1109/ICCV48922.2021.00986.
[6]	LIANG Jingyun, CAO Jiezhang, SUN Guolei, et al. SwinIR: Image restoration using Swin transformer[C]. The 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), Montreal, Canada, 2021: 1833–1844. doi: 10.1109/ICCVW54120.2021.00210.
[7]	CHEN Zheng, ZHANG Yulun, GU Jinjin, et al. Cross aggregation transformer for image restoration[C]. The 36th International Conference on Neural Information Processing Systems, New Orleans, USA, 2022: 1847.
[8]	SHI Jinpeng, LI Hui, LIU Tianle, et al. Image super-resolution using efficient striped window transformer[EB/OL]. https://arxiv.org/abs/2301.09869, 2023.
[9]	WU Sitong, WU Tianyi, TAN Haoru, et al. Pale transformer: A general vision transformer backbone with pale-shaped attention[C]. The 36th AAAI Conference on Artificial Intelligence, Palo Alto, USA, 2022: 2731–2739. doi: 10.1609/aaai.v36i3.20176.
[10]	WU Gang, JIANG Junjun, JIANG Kui, et al. Content-aware transformer for all-in-one image restoration[EB/OL]. https://arxiv.org/abs/2504.04869v1, 2025.
[11]	ZHANG Jiale, ZHANG Yulun, GU Jinjin, et al. Accurate image restoration with attention retractable transformer[C]. The Eleventh International Conference on Learning Representations, Kigali, Rwanda, 2023: 1–13.
[12]	CHEN Zheng, ZHANG Yulun, GU Jinjin, et al. Recursive generalization transformer for image super-resolution[C]. The Twelfth International Conference on Learning Representations, Vienna, Austria, 2024: 1–12.
[13]	CHU Shuchuan, DOU Zhichao, PAN J S, et al. HMANet: Hybrid multi-axis aggregation network for image super-resolution[C].The 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Seattle, USA, 2024: 6257–6266. doi: 10.1109/CVPRW63382.2024.00629.
[14]	YOO J, KIM T, LEE S, et al. Enriched CNN-transformer feature aggregation networks for super-resolution[C]. The 2023 IEEE/CVF Winter Conference on Applications of Computer Vision, Waikoloa, USA, 2023: 4945–4954. doi: 10.1109/WACV56688.2023.00493.
[15]	SI Chenyang, YU Weihao, ZHOU Pan, et al. Inception transformer[C]. The 36th International Conference on Neural Information Processing Systems, New Orleans, USA, 2022: 1707.
[16]	KORKMAZ C, TEKALP A M, and DOGAN Z. Training generative image super-resolution models by wavelet-domain losses enables better control of artifacts[C]. 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, USA, 2024: 5926–5936. doi: 10.1109/CVPR52733.2024.00566.
[17]	韩玉兰, 崔玉杰, 罗轶宏, 等. 基于密集残差和质量评估引导的频率分离生成对抗超分辨率重构网络[J]. 电子与信息学报, 2024, 46(12): 4563–4574. doi: 10.11999/JEIT240388. HAN Yulan, CUI Yujie, LUO Yihong, et al. Frequency separation generative adversarial super-resolution reconstruction network based on dense residual and quality assessment[J]. Journal of Electronics & Information Technology, 2024, 46(12): 4563–4574. doi: 10.11999/JEIT240388.
[18]	LI Ao, ZHANG Le, LIU Yun, et al. Feature modulation transformer: Cross-refinement of global representation via high-frequency prior for image super-resolution[C]. The 2023 IEEE/CVF International Conference on Computer Vision (ICCV), Paris, France, 2023: 12480–12490. doi: 10.1109/iccv51070.2023.01150.
[19]	YAO Hongdou, HAN Pengfei, WANG Xiaofen, et al. Super-resolution via hierarchical attention and detail enhancement transformer network[J]. Optics & Laser Technology, 2025, 188: 112836. doi: 10.1016/j.optlastec.2025.112836.
[20]	程德强, 袁航, 钱建生, 等. 基于深层特征差异性网络的图像超分辨率算法[J]. 电子与信息学报, 2024, 46(3): 1033–1042. doi: 10.11999/JEIT230179. CHENG Deqiang, YUAN Hang, QIAN Jiansheng, et al. Image super-resolution algorithms based on deep feature differentiation network[J]. Journal of Electronics & Information Technology, 2024, 46(3): 1033–1042. doi: 10.11999/JEIT230179.
[21]	寇旗旗, 刘规, 江鹤, 等. 基于多域信息增强的轻量级图像超分辨率网络[J]. 通信学报, 2025, 46(4): 144–159. doi: 10.11959/j.issn.1000-436x.2025059. KOU Qiqi, LIU Gui, JIANG He, et al. Lightweight image super-resolution network based on muti-domain information enhancement[J]. Journal on Communications, 2025, 46(4): 144–159. doi: 10.11959/j.issn.1000-436x.2025059.
[22]	WANG Xintao, XIE Liangbin, DONG Chao, et al. Real-ESRGAN: Training real-world blind super-resolution with pure synthetic data[C]. The 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), Montreal, Canada, 2021: 1905–1914. doi: 10.1109/ICCVW54120.2021.00217.
[23]	WANG Yufei, YANG Wenhan, CHEN Xinyuan, et al. SinSR: Diffusion-based image super-resolution in a single step[C]. The 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, USA, 2024: 25796–25805. doi: 10.1109/CVPR52733.2024.02437.