Single Image-Based Reflection Removal via Dual-Stream Multi-Column Reversible Encoding
Source abstract
Abstract
Reflection removal from a single image is an ill-posed problem due to the inherent ambiguity in separating transmission and reflection components from a single composite observation. In this paper, we address this challenge by introducing a reversible feature encoding strategy combined with a simplified dual-stream decoding structure. In particular, the reversible NAFNet encoder enables us to retain all feature information throughout the encoding process while avoiding memory overhead, an aspect that is crucial for separating overlapping structures. In place of complex gated mechanisms, the proposed dual-stream decoder leverages shared encoder features and skip connections, thus enabling implicit bidirectional information flow between transmission and reflection streams. Although our model adopts a lightweight structure and omits attention modules, it achieves competitive results on standard reflection removal benchmarks, indicating that efficient and interpretable designs can match or surpass more complex counterparts.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Steganography and Watermarking Techniques · Image Enhancement Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Computer Engineering, Keimyung University, Daegu 42601, Republic of Korea
Funding
Keimyung University
References (30)
Show source-provided references
1. Inpainting GAN-based image blending with adaptive binary line mask10.33851/JMIS.2023.10.3.227 ↗
2. Anti-Occlusion Diagnosis of Skin Cancer Based on Heterogeneous Data10.33851/JMIS.2025.12.2.51 ↗
3. Image Reconstruction Method by Spatial Feature Prediction Using CNN and Attention10.33851/JMIS.2024.11.1.1 ↗
4. User assisted separation of reflections from a single image using a sparsity prior10.1109/TPAMI.2007.1106 ↗
5. Wan, R., Shi, B., Duan, L.Y., Tan, A.H., and Kot, A.C. (2018, January 18–22). CRRN: Multi-scale guided concurrent reflection removal network. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.10.1109/CVPR.2018.00502 ↗
6. Yang, J., Gong, D., Liu, L., and Shi, Q. (2018, January 8–14). Seeing deeply and bidirectionally: A deep learning approach for single image reflection removal. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.10.1007/978-3-030-01219-9_40 ↗
7. Wen, Q., Tan, Y., Qin, J., Liu, W., Han, G., and He, S. (2019, January 16–20). Single Image Reflection Removal Beyond Linearity. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.10.1109/CVPR.2019.00389 ↗
8. Hu, Q., and Guo, X. (2023, January 2–6). Single Image Reflection Separation via Component Synergy. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Paris, France.10.1109/ICCV51070.2023.01208 ↗
9. Zhang, X., Ng, R., and Chen, Q. (2018, January 18–22). Single image reflection separation with perceptual losses. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.10.1109/CVPR.2018.00503 ↗
10. Wei, K., Yang, J., Fu, Y., Wipf, D., and Huang, H. (2019, January 15–20). Single image reflection removal exploiting misaligned training data and network enhancements. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00837 ↗
11. Zhao, H., Li, M., Hu, Q., and Guo, X. (2025, January 11–15). Reversible decoupling network for single image reflection removal. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.10.1109/CVPR52734.2025.02461 ↗
12. Chen, L., Chu, X., Zhang, X., and Sun, J. (2022, January 23–27). Simple baselines for image restoration. Proceedings of the European Conference on Computer Vision (ECCV), Tel Aviv, Israel.10.1007/978-3-031-20071-7_2 ↗
13. Li, Y., and Brown, M.S. (2014, January 23–28). Single image layer separation using relative smoothness. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, OH, USA.10.1109/CVPR.2014.346 ↗
14. Schechner, Y.Y., Shamir, J., and Kiryati, N. (1999, January 20–27). Polarization-based decorrelation of transparent layers: The inclination angle of an invisible surface. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Corfu, Greece.10.1109/ICCV.1999.790305 ↗
15. Wan, R., Pan, B., Xia, L., Yang, M.H., Kang, S.B., and Lu, J. (2016, January 25–28). Depth of field guided reflection removal. Proceedings of the European Conference on Computer Vision (ECCV), Phoenix, AZ, USA.10.1109/ICIP.2016.7532311 ↗
16. Shih, Y., Sunkavalli, K., Paris, S., Durand, F., and Freeman, W.T. (2015, January 7–12). Reflection removal using ghosting cues. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA.
17. Han, X., and Sim, T. (2017, January 21–26). Reflection removal using low-rank matrix completion. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.412 ↗
18. Sirinukulwattana, K., Choe, G., and Kweon, I.S. (2015, January 27–30). Reflection removal using disparity and gradient-sparsity via smoothing algorithm. Proceedings of the IEEE International Conference on Image Processing (ICIP), Quebec City, QC, Canada.10.1109/ICIP.2015.7351139 ↗
19. A computational approach for obstruction-free photography10.1145/2766940 ↗
20. Jin, M., Susstrunk, S., and Favaro, P. (2018, January 4–9). Learning to see through reflections. Proceedings of the IEEE International Conference on Computational Photography (ICCP), Pittsburgh, PA, USA.10.1109/ICCPHOT.2018.8368464 ↗
21. Fan, Q., Yang, J., and Hua, G. (2017, January 22–29). A generic deep architecture for single image reflection removal and image smoothing. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Venice, Italy.10.1109/ICCV.2017.351 ↗
22. Li, C., Yang, Y., He, K., Lin, S., and Hopcroft, J.E. (2020, January 14–19). Single image reflection removal through cascaded refinement. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.10.1109/CVPR42600.2020.00362 ↗
23. Hong, Y., Zhong, H., Weng, S., Liang, J., and Shi, B. (October, January 29). L-DiffER: Single Image Reflection Removal with Language-based Diffusion Model. Proceedings of the European Conference on Computer Vision (ECCV), Milan, Italy.
24. Behrmann, J., Grathwohl, W., Chen, R.T.Q., Duvenaud, D., and Jacobsen, J.H. (2019, January 9–15). Invertible residual networks. Proceedings of the 36th International Conference on Machine Learning (ICML), Long Beach, CA, USA.
25. Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., and Antiga, L. (2019, January 8–14). Pytorch: An imperative style, high-performance deep learning library. Proceedings of the 33rd International Conference on Neural Information Processing Systems (NIPS’19), Vancouver, BC, Canada.
26. Kinga, D., and Adam, J.B. (2014). A method for stochastic optimization. arXiv.
27. Trash or Treasure? An Interactive Dual-Stream Strategy for Single Image Reflection Separation
28. Two-stage single image reflection removal with reflection-aware guidance10.1007/s10489-022-04391-6 ↗
29. The pascal visual object classes (voc) challenge10.1007/s11263-009-0275-4 ↗
30. Dong, Z., Xu, K., Yang, Y., Bao, H., Xu, W., and Lau, R.W. (2021, January 11–17). Location-aware single image reflection removal. Proceedings of the IEEE/CVF International Conference on Computer Vision, Montreal, BC, Canada.10.1109/ICCV48922.2021.00497 ↗