AI summaryⓘ
The authors address the challenge of reconstructing images from lensless cameras, which use thin coded elements instead of traditional lenses but produce complicated blur patterns that are hard to undo. They introduce a new method called the Integrated Forward-Inverse Network (IFIN) that combines model-based physics calculations with learnable neural network steps, allowing the image reconstruction to improve progressively while respecting the physics of the system. This approach also adapts to errors in the system model, leading to better image quality in tests on various difficult lensless imaging data. The authors show that their method works well beyond lensless imaging, like in other image deblurring tasks.
lensless imagingpoint-spread function (PSF)computational imaginginverse problemdeep learningphysics-guided neural networksimage reconstructionmodel mismatchGaussian deblurringholography
Authors
Donggeon Bae, Jaewoo Jung, Yong Guk Kang, Kyung Chul Lee, Taeyoung Kim, Jongho Kim, Sangjun Byun, Joonsik Park, Seung Ah Lee
Abstract
Lensless imaging enables compact and versatile computational cameras by replacing bulky optics with thin coded elements. However, reconstruction from the resulting measurements is challenging: large-footprint point-spread functions (PSFs) produce highly multiplexed observations, making inversion severely ill-conditioned and sensitive to calibration errors and model mismatch. While deep learning approaches, including hybrid models that incorporate physics priors, have shown promise, explicitly maintaining data fidelity throughout the network hierarchy remains difficult. Here, we propose the Integrated Forward-Inverse Network (IFIN), a physics-guided architecture that interleaves differentiable forward projections with learnable inverse updates at every scale, enabling complementary cues to be exploited jointly in the measurement and image domains. This bidirectional coupling supports progressive, physics-consistent refinement and permits system-constrained PSF kernel adaptation under model uncertainty. On challenging lensless benchmarks, including a newly introduced dataset, IFIN achieves state-of-the-art reconstruction quality. We further observe competitive performance on Gaussian deblurring and simulated inline holography reconstruction, suggesting that the same interleaving principle can extend beyond lensless cameras.