WaveletMask: Wavelet-Domain Mask-Guided Degradation Detection for Old-Film Restoration
Source abstract
Abstract
Old films suffer from scratches, dust, and brightness flicker caused by aging film stock and unstable analog exposure. Recurrent restoration frameworks suppress these artifacts under the guidance of degradation masks, yet pixel-domain frame differencing provides weak evidence for thin structural defects and confuses global brightness variation with content change. We present WaveletMask, a wavelet-domain degradation sensing framework that disentangles these two failure modes by construction: a high-frequency branch localizes transient structural defects from Haar detail-band differences between adjacent frames, a low-frequency branch isolates frame-level brightness deviations from coarse approximation responses, and a parameter-free maximum fusion rule passes the dominant cue to the recurrent gate. On the Synthetic and Real-World Old Video (SRWOV) benchmark, WaveletMask attains the best PSNR among ten re-trained methods (26.60 dB, +0.61 dB over the strongest competitor), and a paired comparison against the Recurrent Transformer Network (RTN) confirms a +0.45 dB gain while adding only 898 detector parameters. On real archival footage, WaveletMask removes scratches and flicker more cleanly while better preserving film texture and temporal stability. These results indicate that explicit wavelet-domain separation of structural and photometric cues offers a reliable, nearly cost-free upgrade for mask-guided recurrent restoration.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Image Enhancement Techniques · Image and Video Quality Assessment · Thin-Film Transistor Technologies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Shanghai Film Academy, Shanghai University, 788 Guangzhong Road, Shanghai 200072, China
Shanghai Engineering Research Center of Motion Picture Special Effects, Shanghai 200072, China
Institute of Chemical Engineering, Guangdong Academy of Sciences, Guangzhou 510665, China
References (53)
Show source-provided references
1. Kokaram, A.C. (1998). Motion Picture Restoration: Digital Algorithms for Artefact Suppression in Degraded Motion Picture Film and Video, Springer.10.1007/978-1-4471-3485-5 ↗
2. DeepRemaster: Temporal Source-Reference Attention Networks for Comprehensive Video Enhancement10.1145/3355089.3356570 ↗
3. Wan, Z., Zhang, B., Chen, D., and Liao, J. (2022, January 19–24). Bringing Old Films Back to Life. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.
4. Wan, Z., Zhang, B., Chen, D., Zhang, P., Chen, D., Liao, J., and Wen, F. (2020, January 14–19). Bringing Old Photos Back to Life. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Virtual.10.1109/CVPR42600.2020.00282 ↗
5. A Survey of Deep Learning Approaches to Image Restoration10.1016/j.neucom.2022.02.046 ↗
6. Deep Learning on Image Denoising: An Overview10.1016/j.neunet.2020.07.025 ↗
7. Lin, S., and Simo-Serra, E. (2024, January 3–8). Restoring Degraded Old Films with Recursive Recurrent Transformer Networks. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, USA.10.1109/WACV57701.2024.00658 ↗
8. Mao, Y., Luo, H., Zhong, Z., Chen, P., Zhang, Z., and Wang, S. (2025, January 11–15). Making Old Film Great Again: Degradation-aware State Space Model for Old Film Restoration. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.10.1109/CVPR52734.2025.02611 ↗
9. Guo, H., Li, J., Dai, T., Ouyang, Z., Ren, X., and Xia, S.T. (October, January 29). MambaIR: A Simple Baseline for Image Restoration with State-Space Model. Proceedings of the Computer Vision—ECCV 2024, Milan, Italy.10.1007/978-3-031-72649-1_13 ↗
10. A Theory for Multiresolution Signal Decomposition: The Wavelet Representation10.1109/34.192463 ↗
11. Drive-by Damage Detection and Localization Exploiting Continuous Wavelet Transform and Multiple Sparse Autoencoders10.1007/s40534-025-00393-5 ↗
12. Liu, P., Zhang, H., Zhang, K., Lin, L., and Zuo, W. (2018, January 18–22). Multi-Level Wavelet-CNN for Image Restoration. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Salt Lake City, UT, USA.10.1109/CVPRW.2018.00121 ↗
13. Detection of Missing Data in Image Sequences10.1109/83.469931 ↗
14. Reconstruction of Degraded Image Sequences. Application to Film Restoration10.1016/S0262-8856(00)00091-3 ↗
15. Correction of Intensity Flicker in Old Film Sequences10.1109/76.795054 ↗
16. Video Restoration Based on Deep Learning: A Comprehensive Survey10.1007/s10462-022-10302-5 ↗
17. Chan, K.C., Wang, X., Yu, K., Dong, C., and Loy, C.C. (2021, January 19–25). BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyond. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Virtual.
18. Chan, K.C., Zhou, S., Xu, X., and Loy, C.C. (2022, January 19–24). BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.10.1109/CVPR52688.2022.00588 ↗
19. Ranjan, A., and Black, M.J. (2017, January 21–26). Optical Flow Estimation Using a Spatial Pyramid Network. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.291 ↗
20. Teed, Z., and Deng, J. (2020, January 23–28). RAFT: Recurrent All-Pairs Field Transforms for Optical Flow. Proceedings of the Computer Vision—ECCV 2020, Glasgow, UK.10.1007/978-3-030-58536-5_24 ↗
21. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., and Polosukhin, I. (2017, January 4–9). Attention Is All You Need. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA.
22. Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., and Guo, B. (2021, January 11–17). Swin Transformer: Hierarchical Vision Transformer Using Shifted Windows. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Virtual.10.1109/ICCV48922.2021.00986 ↗
23. Liang, J., Fan, Y., Xiang, X., Ranjan, R., Ilg, E., Green, S., Cao, J., Zhang, K., Timofte, R., and Van Gool, L. (December, January 28). Recurrent Video Restoration Transformer with Guided Deformable Attention. Proceedings of the Advances in Neural Information Processing Systems, New Orleans, LA, USA.
24. VRT: A Video Restoration Transformer10.1109/TIP.2024.3372454 ↗
25. Li, D., Shi, X., Zhang, Y., Cheung, K.C., See, S., Wang, X., Qin, H., and Li, H. (2023, January 17–24). A Simple Baseline for Video Restoration with Grouped Spatial-Temporal Shift. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada.10.1109/CVPR52729.2023.00947 ↗
26. Liang, J., Cao, J., Sun, G., Zhang, K., Van Gool, L., and Timofte, R. (2021, January 11–17). SwinIR: Image Restoration Using Swin Transformer. Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), Virtual.10.1109/ICCVW54120.2021.00210 ↗
27. Zamir, S.W., Arora, A., Khan, S., Hayat, M., Khan, F.S., and Yang, M.H. (2022, January 19–24). Restormer: Efficient Transformer for High-Resolution Image Restoration. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.10.1109/CVPR52688.2022.00564 ↗
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 Workshops (ICCVW), Virtual.10.1109/ICCVW54120.2021.00217 ↗
29. Zeng, Y., Fu, J., and Chao, H. (2020, January 23–28). Learning Joint Spatial-Temporal Transformations for Video Inpainting. Proceedings of the Computer Vision—ECCV 2020, Glasgow, UK.10.1007/978-3-030-58517-4_31 ↗
30. Zhou, S., Li, C., Chan, K.C., and Loy, C.C. (2023, January 2–6). ProPainter: Improving Propagation and Transformer for Video Inpainting. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Paris, France.10.1109/ICCV51070.2023.00961 ↗
31. Huang, H., He, R., Sun, Z., and Tan, T. (2017, January 22–29). Wavelet-SRNet: A Wavelet-Based CNN for Multi-Scale Face Super Resolution. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Venice, Italy.10.1109/ICCV.2017.187 ↗
32. Deng, X., Yang, R., Xu, M., and Dragotti, P.L. (November, January 27). Wavelet Domain Style Transfer for an Effective Perception-Distortion Tradeoff in Single Image Super-Resolution. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Republic of Korea.
33. Wavelet-Based Optical Flow Estimation10.1109/76.981841 ↗
34. The Dual-Tree Complex Wavelet Transform10.1109/MSP.2005.1550194 ↗
35. Li, B., Liu, X., Hu, P., Wu, Z., Lv, J., and Peng, X. (2022, January 19–24). All-in-One Image Restoration for Unknown Corruption. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.10.1109/CVPR52688.2022.01693 ↗
36. Potlapalli, V., Zamir, S.W., Khan, S.H., and Khan, F.S. (2023, January 10–16). PromptIR: Prompting for All-in-One Image Restoration. Proceedings of the Advances in Neural Information Processing Systems, New Orleans, LA, USA.10.52202/075280-3121 ↗
37. Johnson, J., Alahi, A., and Li, F.F. (2016, January 8–16). Perceptual Losses for Real-Time Style Transfer and Super-Resolution. Proceedings of the Computer Vision—ECCV 2016, Amsterdam, The Netherlands.
38. Simonyan, K., and Zisserman, A. (2015, January 7–9). Very Deep Convolutional Networks for Large-Scale Image Recognition. Proceedings of the International Conference on Learning Representations (ICLR), San Diego, CA, USA.
39. Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2014, January 8–13). Generative Adversarial Nets. Proceedings of the Advances in Neural Information Processing Systems, Montreal, QC, Canada.
40. Nah, S., Baik, S., Hong, S., Moon, G., Son, S., Timofte, R., and Lee, K.M. (2019, January 16–20). NTIRE 2019 Challenge on Video Deblurring and Super-Resolution: Dataset and Study. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Long Beach, CA, USA.10.1109/CVPRW.2019.00251 ↗
41. Antic, J. (2026, April 01). DeOldify. Available online: https://github.com/jantic/DeOldify.
42. Kingma, D.P., and Ba, J. (2015, January 7–9). Adam: A Method for Stochastic Optimization. Proceedings of the International Conference on Learning Representations (ICLR), San Diego, CA, USA.
43. Wang, X., Xie, L., Yu, K., Chan, K.C., Loy, C.C., and Dong, C. (2026, April 01). BasicSR: Open Source Image and Video Restoration Toolbox. GitHub Repository. Available online: https://github.com/XPixelGroup/BasicSR.
44. Image Quality Assessment: From Error Visibility to Structural Similarity10.1109/TIP.2003.819861 ↗
45. Zhang, R., Isola, P., Efros, A.A., Shechtman, E., and Wang, O. (2018, January 18–22). The Unreasonable Effectiveness of Deep Features as a Perceptual Metric. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.10.1109/CVPR.2018.00068 ↗
46. Image Quality Assessment: Unifying Structure and Texture Similarity
47. Making a “Completely Blind” Image Quality Analyzer10.1109/LSP.2012.2227726 ↗
48. No-Reference Image Quality Assessment in the Spatial Domain10.1109/TIP.2012.2214050 ↗
49. Exploring CLIP for Assessing the Look and Feel of Images
50. Kim, K., Kim, Y., and Kim, Y.J. (2025). Hybrid Frequency–Spatial Domain Learning for Image Restoration in Under-Display Camera Systems Using Augmented Virtual Big Data Generated by the Angular Spectrum Method. Appl. Sci., 15.10.2139/ssrn.4705827 ↗
51. Park, C.H., Choi, H.D., and Lim, M.T. (2025). Harnessing Spatial-Frequency Information for Enhanced Image Restoration. Appl. Sci., 15.10.3390/app15041856 ↗
52. Rubel, A., Ieremeiev, O., Lukin, V., Fastowicz, J., and Okarma, K. (2022). Combined No-Reference Image Quality Metrics for Visual Quality Assessment Optimized for Remote Sensing Images. Appl. Sci., 12.10.3390/app12041986 ↗
53. Yeo, W.H., and Ryu, H.C. (2025). An Integration Framework for the Inpainting and Colorization of Arbitrary Masked Grayscale Images. Appl. Sci., 15.10.3390/app15041978 ↗