Integrated Forward-Inverse Network for Lensless Image Reconstruction
This work provides a significant improvement in image reconstruction quality for lensless cameras, benefiting applications requiring compact and versatile imaging systems.
This paper addresses the challenge of lensless image reconstruction, where large point-spread functions lead to ill-conditioned inversions. The authors propose the Integrated Forward-Inverse Network (IFIN), which interleaves differentiable forward projections with learnable inverse updates, achieving state-of-the-art reconstruction quality on lensless benchmarks and competitive performance on Gaussian deblurring and simulated inline holography.
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.