Instance-Aware Image Restoration under Unknown Real-World Degradations and Resolution Variations
DOI:
https://doi.org/10.66857/jirt.v3i2.48Keywords:
Image Restoration, Instance-Aware Learning, Blind Degradation, Implicit Neural RepresentationsAbstract
The problem of image restoration has traditionally been constrained by assumptions of synthetic, uniformly applied degradation models, such as bicubic downsampling or Gaussian noise, which consistently fail to generalize to the immense complexity of real-world scenarios. Furthermore, the advent of varied imaging sensors has introduced continuous resolution variations, rendering fixed-scale models largely obsolete. This paper presents a novel instance-aware image restoration framework designed to operate under completely unknown real-world degradations and continuous resolution variations. By conceptualizing the image not as a homogeneous field of pixels but as a composition of distinct semantic instances, the proposed methodology dynamically adapts its restoration filters based on localized, instance-specific degradation estimations. This localized approach allows the system to differentiate between the varying restoration requirements of complex foreground subjects and heterogeneous background textures. Through the integration of an implicit neural representation module, the framework achieves continuous resolution adaptation, circumventing the limitations of discrete scale-specific upsampling modules. The synergistic coupling of instance-aware degradation representation learning and continuous coordinate-based decoding constructs a robust pipeline capable of handling unprecedented variations in input fidelity. Extensive empirical evaluations on diverse real-world datasets demonstrate that the proposed architecture establishes a new paradigm in blind image restoration, achieving superior quantitative metrics and preserving high-frequency structural details across arbitrary magnification factors.
References
1. Xia, Y., & Ma, J. (2026). Locality Optimization Refinement with Deformation for Shape Matching via Functional Maps.International Journal of Computer Vision,134(2), 76.
2. Caron, M., Touvron, H., Misra, I., Jégou, H., Mairal, J., Bojanowski, P., & Joulin, A. (2021). Emerging properties in self-supervised vision transformers. In Proceedings of ICCV.
3. Zhou, Yufan, et al. "Masked Temporal Interpolation Diffusion for Procedure Planning in Instructional Videos." arXiv preprint arXiv:2507.03393 (2025).
4. Wang, J., Malawade, A. V., Zhou, J., Yu, S. Y., & Al Faruque, M. A. (2024, January). Rs2g: Data-driven scene-graph extraction and embedding for robust autonomous perception and scenario understanding. In 2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) (pp. 7478-7487). IEEE.
5. Zhang, W., Huang, M., Zhou, Y., Zhang, J., Yu, J., Wang, J., & Xu, L. (2024). Both2hands: Inferring 3d hands from both text prompts and body dynamics. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 2393-2404).
6. Xia, Y., & Ma, J. (2022). Locality-guided global-preserving optimization for robust feature matching.IEEE Transactions on Image Processing,31, 5093-5108.
7. Zhang B, Wang X, Kao H, et al. Consensus Matrix: A Role Specialized Multi Agent Framework for Structured Collaborative Decision Making in Agentic Visual Media Workflows[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2026: 4613 4622.
8. Huang, H., Zhang, J., Zhang, J., Xu, J., & Wu, Q. (2020). Low-rank pairwise alignment bilinear network for few-shot fine-grained image classification.IEEE Transactions on Multimedia,23, 1666-1680.
9. Wang, H., Que, H., Xu, Q., Liu, M., Zhou, W., Feng, J., ... & Lin, F. (2026, April). Reverse-engineered reasoning for open-ended generation. In International Conference on Learning Representations (Vol. 2026, pp. 45563-45589).
10. Xia, Y., Ye, T., Huang, J., Mei, X., & Ma, J. (2026, March). Probabilistic deformation consistency for unsupervised shape matching. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 40, No. 13, pp. 10951-10959).
11. Cong, P., Xu, Y., Ren, Y., Zhang, J., Xu, L., Wang, J., ... & Ma, Y. (2023, June). Weakly supervised 3d multi-person pose estimation for large-scale scenes based on monocular camera and single lidar. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 37, No. 1, pp. 461-469).
12. Li, Q., Xu, T., Luo, T., Zhong, Y., Li, Y., Zhou, Y., & Hou, C. (2026). Theory-driven label-specific representation for incomplete multi-view multi-label learning. Advances in Neural Information Processing Systems, 38, 121996-122037.
13. Chen, L., Jiang, X., Liu, X., & Zhou, Z. (2021). Logarithmic norm regularized low-rank factorization for matrix and tensor completion. IEEE Transactions on Image Processing, 30, 3434-3449.
14. Zhou, J., Shuang, K., Wang, Q., Qian, B., & Guo, J. (2025). Bi-directional feature learning-based approach for zero-shot event argument extraction. Information Processing & Management, 62(5), 104199.
15. Yang, Y., & Zhang, S. (2025). Pixel-wise calibration for a multi-focus microscopic 3D imaging system.Optics and Lasers in Engineering,194, 109127.
16. Qi, Z., Yuan, Y., Ruan, X., Wang, S., Zhang, W., & Huang, Q. (2024, March). Bias-conflict sample synthesis and adversarial removal debias strategy for temporal sentence grounding in video. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 38, No. 5, pp. 4533-4541).
17. Qi, Z., Yuan, Y., Ruan, X., Wang, S., Zhang, W., & Huang, Q. (2024). Collaborative debias strategy for temporal sentence grounding in video. IEEE Transactions on Circuits and Systems for Video Technology, 34(11), 10972-10986.
18. Li, X., Yang, F., Chen, L., & Cai, H. (2016, July). Saliency transfer: An example-based method for salient object detection. In IJCAI (pp. 3411-3417).
19. Peng, Qucheng, et al. "3d vision-language gaussian splatting." International Conference on Learning Representations. Vol. 2025. 2025.
20. Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2022). High-resolution image synthesis with latent diffusion models. In Proceedings of CVPR.
21. Lee, Y., Gao, P., Xu, Y., & Fan, W. (2025, October). How Do Optical Flow and Textual Prompts Collaborate to Assist in Audio-Visual Semantic Segmentation?. In 2025 IEEE/CVF International Conference on Computer Vision (ICCV) (pp. 23342-23352). IEEE.
22. Qu, D., & Ma, Y. (2026). Fourier–Transformer Mixer Network for Efficient Video Scene Graph Prediction.Engineering Proceedings,120(1), 16.
23. Li, B., Zhang, R., Liang, H., Zhang, J., Zhang, J., Chen, X., ... & Wang, J. (2026). Interagent: Physics-based multi-agent command execution via diffusion on interaction graphs. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 15253-15265).
24. Li, Z., Chen, Z., Qu, F., Wang, M., Zhao, Y., Zhang, K., & Peng, Y. (2024). Point resampling and ray transformation aid to editable NeRF models. arXiv preprint arXiv:2405.07306.
25. Zhao, H., Wang, Q., Zhan, G., Min, W., Zou, Y., & Cui, S. (2022). Need only one more point (NOOMP): Perspective adaptation crowd counting in complex scenes. IEEE Transactions on Multimedia, 25, 1414-1426.
26. Li, Q., Liu, Z., Xu, T., Luo, T., & Hou, C. (2026). Adaptive Disentangled Representation Learning for Incomplete Multi-View Multi-Label Classification. arXiv preprint arXiv:2601.05785.
27. Gao, P., Lee, Y., Zhang, H., Chen, Z., & Liu, X. (2024, December). Dynamic identity-guided attention network for visible-infrared person re-identification. In International Conference on Neural Information Processing (pp. 364-379). Singapore: Springer Nature Singapore.
28. Wang, H., Xu, Q., Wang, C., Xue, T., Peng, C., Chen, W., & Lin, F. (2026). Bad Seeing or Bad Thinking? Rewarding Perception for Multimodal Reasoning.arXiv preprint arXiv:2605.14054.
29. Qu, W., Wang, J., Gong, Y., Huang, X., & Xiao, L. (2025, June). An end-to-end robust point cloud semantic segmentation network with single-step conditional diffusion models. In 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 27325-27335). IEEE.
30. Xia, Y., & Ma, J. (2025). Grid-guided sparse Laplacian consensus for robust feature matching.IEEE Transactions on Image Processing,34, 1367-1381.
31. Liu, C., Ma, L., Zhang, X. T., Zhang, Y., Zhang, H., Yang, X., & Tian, F. (2026). Boosting omni-modal language models: Staged post-training with visually debiased evaluation. arXiv preprint arXiv:2605.12034.
32. Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., & Joulin, A. (2020). Unsupervised learning of visual features by contrasting cluster assignments. In Advances in Neural Information Processing Systems.
33. Yang, Y., & Zhang, S. (2024). Pixelwise calibration method for a telecentric structured light system.Applied Optics,63(10), 2562-2569.
34. Wang, M., Li, J., Li, Z., Luo, C., Chen, B., Xia, S. T., & Wang, Z. (2023, October). Unsupervised anomaly detection with local-sensitive VQVAE and global-sensitive transformers. In 2023 IEEE International Conference on Image Processing (ICIP) (pp. 1080-1084). IEEE.
35. Chen, L., Yang, Y., & Zhang, S. (2024, September). Rapid autofocusing method for digital fringe projection techniques. In Interferometry and Structured Light 2024(Vol. 13135, pp. 92-97). SPIE.
36. Wang, Y., Fang, Y., Wang, T., Feng, Y., Tan, Y., Zhang, S., ... & Xu, R. (2025). Dreamnav: A trajectory-based imaginative framework for zero-shot vision-and-language navigation.arXiv preprint arXiv:2509.11197.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Chen Han, Jun Shi
This work is licensed under a Creative Commons Attribution 4.0 International License.
All articles in the Journal of Innovative Research and Technology are licensed under Creative Commons Attribution 4.0 (CC BY 4.0). Users can share, adapt, and build upon the material with appropriate credit, without additional restrictions.
