Mural restoration via the fusion of edge-guided and multi-scale spatial features
Source abstract
Abstract
To address the issues of low contrast and blurred edges in Dunhuang murals, which often lead to artifacts and edge-detail distortions in restored areas, this study proposes a mural restoration algorithm via the fusion of edge-guided and multi-scale spatial features. First, an encoder extracts low-level features, and an Edge-Gaussian Fusion Block enhances edge details using a rotation-invariant Scharr filter and Gaussian modeling to refine low-confidence features. In the decoding phase, a hybrid pyramid fusion mamba block applies dense spatial pyramid pooling to aggregate multi-scale semantic information, while a Pyramid Fusion Mamba Module reduces redundant semantics for improved feature expressiveness. Finally, a Spatially Enhanced Mamba Module captures long-range dependencies and performs pixel-level restoration. Experiments on the Dunhuang mural dataset show significant improvements: PSNR increases by 0.04–0.67%, SSIM improves by 0.71–0.84%, L1 error reduces by 10.47–20.95%, and LPIPS decreases by 1.18–14.45%.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: 3D Surveying and Cultural Heritage · Image Processing and 3D Reconstruction · Archaeological Research and Protection
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (38)
Show source-provided references
1. Chen, Y. et al. Dunhuang mural restoration algorithm based on Gabor transform and group sparse representation. Laser Optoelectron. Prog. 57, 175–184 (2020).10.3788/LOP57.111400 ↗
2. Lv, J., Shao, L. & Lei, X. A survey of image inpainting algorithms based on deep neural networks. Comput. Eng. Appl. 59, 1–12 (2023).
3. Tschumperlé, D. & Deriche, R. Vector-valued image regularization with PDEs: a common framework for different applications. IEEE Trans. Pattern Anal. Mach. Intell. 27, 506–517 (2005).10.1109/TPAMI.2005.87 ↗
4. Ronneberger, O., Fischer, P. & Brox, T. U-net: Convolutional Networks for Biomedical Image Segmentation. In Medical image computing and computer-assisted intervention—MICCAI 2015 234–241 (Springer International Publishing, 2015).10.1007/978-3-319-24574-4_28 ↗
5. Wei, L. Y. & Levoy, M. Fast texture synthesis using tree-structured vector quantization. Proc. 27th Annu. Conf. Comput. Graph. Interact. Tech. 479, 488 (2000).
6. Goodfellow, I. J., Pouget-Abadie, J. & Mirza, M. Generative adversarial nets. Adv. Neural Inf. Process. Syst. https://dl.acm.org/doi/10.1145/3422622 (2014).
7. Li, Y., Hou, Q. & Zheng, Z. Large selective kernel network for remote sensing object detection. Proc. IEEE/CVF Int. Conf. Comput. Vis. 16794, 16805 (2023).
8. Cai, X., Lai, Q. & Wang, Y. Poly kernel inception network for remote sensing detection. Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. 27706, 27716 (2024).
9. Iizuka, S., Simo-Serra, E. & Ishikawa, H. Globally and locally consistent image completion. ACM Trans. Graph. 36, 1–14 (2017).10.1145/3072959.3073659 ↗
10. Yang, C., Lu, X. & Lin, Z. High-resolution image inpainting using multi-scale neural patch synthesis. Proc. IEEE Conf. Comput. Vis. Pattern Recognit. 6721, 6729 (2017).
11. Zhang, X., Wang, X. & Shi, C. De-GAN: domain embedded GAN for high quality face image inpainting. Pattern Recognit 124, 108415–108427 (2022).10.1016/j.patcog.2021.108415 ↗
12. Tian, H. et al. Pyramid-VAE-GAN: transferring hierarchical latent variables for image inpainting. Comput. Vis. Media 9, 827–841 (2023).10.1007/s41095-022-0331-3 ↗
13. Zeng, Y. et al. Aggregated contextual transformations for high-resolution image inpainting. IEEE Trans. Vis. Comput. Graph. 29, 3266–3280 (2022).10.1109/TVCG.2022.3156949 ↗
14. Cao, L. et al. Generator pyramid for high-resolution image inpainting. Complex Intell. Syst. 9, 6297–6306 (2023).10.1007/s40747-023-01080-w ↗
15. Chen, M. et al. RFA-Net: residual feature attention network for fine-grained image inpainting. Eng. Appl. Artif. Intell. 119, 105814–105824 (2023).10.1016/j.engappai.2022.105814 ↗
16. Feng, X. et al. Hierarchical contrastive learning for pattern-generalizable image corruption detection. In Proc. IEEE/CVF International Conference on Computer Vision 12076–12085 (IEEE, 2023).10.1109/ICCV51070.2023.01109 ↗
17. Dong, Q., Cao, C. & Fu, Y. Incremental transformer structure enhanced image inpainting with masking positional encoding. In Proc IEEE/CVF Conference on Computer Vision Pattern Recognition 11358–11368 (IEEE, 2022).10.1109/CVPR52688.2022.01107 ↗
18. Miao, W. et al. ITrans: generative image inpainting with transformers. Multimed. Syst. 30, 21–33 (2024).10.1007/s00530-023-01211-w ↗
19. Li, W. et al. MAT: mask-aware transformer for large hole image inpainting. In Proc IEEE/CVF Conference on Computer Vision Pattern Recognition 10758–10768 (IEEE, 2022).10.1109/CVPR52688.2022.01049 ↗
20. Shamsolmoali, P., Zareapoor, M. & Granger, E. TransInpaint: transformer-based image inpainting with context adaptation. Proc. IEEE/CVF Int. Conf. Comput. Vis. 849, 858 (2023).
21. Zhao, L. et al. UCTGAN: diverse image inpainting based on unsupervised cross-space translation. In Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition 5741–5750 (IEEE, 2020).10.1109/CVPR42600.2020.00578 ↗
22. Chen, H. et al. Pre-trained image processing transformer. In Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition 12299–12310 (IEEE, 2021).10.1109/CVPR46437.2021.01212 ↗
23. Zamir, S. W. et al. Restormer: efficient transformer for high-resolution image restoration. In Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition 5728–5739 (IEEE, 2022).10.1109/CVPR52688.2022.00564 ↗
24. Suvorov, R. et al. Resolution-robust large mask inpainting with Fourier convolutions. In Proc. IEEE/CVF Winter Conference on Applications of Computer Vision 2149–2159 (IEEE, 2022).10.1109/WACV51458.2022.00323 ↗
25. Liu, Y. et al. Vmamba: visual state space model. Adv. Neural Inf. Process. Syst. 37, 103031–103063 (2024).
26. Chen, S. et al. SEM-Net: efficient pixel modelling for image inpainting with spatially enhanced SSM. In Proc. IEEE/CVF Winter Conference on Applications of Computer Vision 461–471 (IEEE, 2025).10.1109/WACV61041.2025.00055 ↗
27. Gu, A., Goel, K. & Ré, C. Efficiently modeling long sequences with structured state spaces. Preprint at https://arxiv.org/abs/2111.00396 (2021).
28. Bibi, N. & Dawood, H. SEBR: scharr edge-based regularization method for blind image deblurring. Arab. J. Sci. Eng. 49, 3435–3451 (2024).10.1007/s13369-023-07986-4 ↗
29. Gu, A. & Dao, T. Mamba: linear-time sequence modeling with selective state spaces. Preprint at https://arxiv.org/abs/2312.00752 (2023).
30. Liu, G. et al. Image inpainting for irregular holes using partial convolutions. In Proc. European Conference on Computer Vision 85–100 (Springer, 2018).10.1007/978-3-030-01252-6_6 ↗
31. Quan, W. et al. Image inpainting with local and global refinement. IEEE Trans. Image Process. 31, 2405–2420 (2022).10.1109/TIP.2022.3152624 ↗
32. Wang, N., Zhang, Y. & Zhang, L. Dynamic selection network for image inpainting. IEEE Trans. Image Process. 30, 1784–1798 (2021).10.1109/TIP.2020.3048629 ↗
33. Deng, Y. et al. T-former: an efficient transformer for image inpainting. In Proc. 30th ACM International Conference on Multimedia. 6559–6568 (ACM, 2022).10.1145/3503161.3548446 ↗
34. Chen, S., Atapour-Abarghouei, A. & Shum, H. P. H. HINT: high-quality inpainting transformer with mask-aware encoding and enhanced attention. IEEE Trans. Multimedia 26, 7649–7660 (2024).10.1109/TMM.2024.3369897 ↗
35. Karras, T., Laine, S. & Aila, T. A style-based generator architecture for generative adversarial networks. In Proc. IEEE/CVF Conference on Computer Vision Pattern Recognition 4401–4410 (IEEE, 2019).10.1109/CVPR.2019.00453 ↗
36. Lu, W. et al. LegNet: lightweight edge-Gaussian driven network for low-quality remote sensing image object detection. Preprint at https://arxiv.org/abs/2503.14012 (2025).
37. Wang, L. et al. PyramidMamba: rethinking pyramid feature fusion with selective space state model for semantic segmentation of remote sensing imagery. Preprint at https://arxiv.org/abs/2406.10828 (2024).
38. Yu, T. et al. Dunhuang Grottoes painting dataset and benchmark. Herit. Sci. 8, 15 (2020).10.1186/s40494-020-0353-z ↗