{"type":"ScholarlyArticle","title":"LensNet: An End-to-End Learning Framework for Empirical Point Spread Function Modeling and Lensless Imaging Reconstruction","authors":[{"name":"Jiesong Bai","slug":"jiesong-bai","given":"Jiesong","family":"Bai","affiliation":""},{"name":"Yuhao Yin","slug":"yuhao-yin","given":"Yuhao","family":"Yin","affiliation":""},{"name":"Yihang Dong","slug":"yihang-dong","given":"Yihang","family":"Dong","affiliation":""},{"name":"Xiaofeng Zhang","slug":"xiaofeng-zhang","given":"Xiaofeng","family":"Zhang","affiliation":""},{"name":"Chi-Man Pun","slug":"chi-man-pun","given":"Chi-Man","family":"Pun","affiliation":""},{"name":"Xuhang Chen","slug":"xuhang-chen","given":"Xuhang","family":"Chen","affiliation":""}],"abstract":"Lensless imaging stands out as a promising alternative to conventional lens-based systems, particularly in scenarios demanding ultracompact form factors and cost-effective architectures. However, such systems are fundamentally governed by the Point Spread Function (PSF), which dictates how a point source contributes to the final captured signal. Traditional lensless techniques often require explicit calibrations and extensive pre-processing, relying on static or approximate PSF models. These rigid strategies can result in limited adaptability to real-world challenges, including noise, system imperfections, and dynamic scene variations, thus impeding high-fidelity reconstruction. In this paper, we propose LensNet, an end-to-end deep learning framework that integrates spatial-domain and frequency-domain representations in a unified pipeline. Central to our approach is a learnable Coded Mask Simulator (CMS) that enables dynamic, data-driven estimation of the PSF during training, effectively mitigating the shortcomings of fixed or sparsely calibrated kernels. By embedding a Wiener filtering component, LensNet refines global structure and restores fine-scale details, thus alleviating the dependency on multiple handcrafted pre-processing steps. Extensive experiments demonstrate LensNet's robust performance and superior reconstruction quality compared to state-of-the-art methods, particularly in preserving high-frequency details and attenuating noise. The proposed framework establishes a novel convergence between physics-based modeling and data-driven learning, paving the way for more accurate, flexible, and practical lensless imaging solutions for applications ranging from miniature sensors to medical diagnostics. The link of code is https://github.com/baijiesong/Lensnet.","doi":"10.24963/ijcai.2025/77","url":"https://ijcai.org/proceedings/2025/77","pdf":"https://ijcai.org/proceedings/2025/0077.pdf","markdown":"https://ijcai.org/proceedings/2025/77.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/77","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"Computer Vision","track":"Main Track","number":77,"pages":{"first":684,"last":692},"keywords":["Computer Vision: CV: Computational photography","Computer Vision: CV: Low-level Vision"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}