Fang, F., Liang, X., Yang, M., Zheng, J., Mass, T., Sun, Y., Yang, X., Xu, X., & Li, Z. (2026). Towards Illumination-Aware Restoration of Metalens-Captured Images: A New Dataset and a Strong Baseline. Proceedings of the AAAI Conference on Artificial Intelligence, 40(25), 21038–21046. https://doi.org/10.1609/aaai.v40i25.39246
Abstract:
Metalenses offer compelling advantages such as lightweight and ultra-thin design, making them promising alternatives to conventional lenses. However, their widespread adoption is hindered by image quality degradation caused by chromatic and angular aberrations. To mitigate this, restoration processes are often necessary to recover high-quality RGB images from metalens-captured inputs. While recent deep learning-based restoration methods show promise, they typically (1) blur or distort peripheral regions, or (2) fail entirely under unseen illumination conditions.
To advance metalens image restoration, we introduce IlluMeta---the first and largest real-world, illumination-aware metalens image dataset—captured across diverse lighting environments. In addition, we propose a novel end-to-end restoration framework that directs attention to challenging regions and adaptively adjusts to varying illuminations via reinforcement learning. Experiments show that our method can be applied in a plug-and-play manner to enhance existing models, significantly improving image restoration quality, especially under unseen lighting conditions, paving the way for broader real-world deployment of metalens technologies.
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the A*STAR - GAP project
Grant Reference no. : I24D1AG062
This research / project is supported by the A*STAR - Manufacturing, Trade, and Connectivity Programmatic Fund
Grant Reference no. : M23L7b0021