Null-Space Diffusion Distillation for Efficient Photorealistic Lensless Imaging

TL;DR

This paper introduces Null-Space Diffusion Distillation (NSDD), a novel method for efficient, ground-truth-free photorealistic lensless imaging that maintains measurement consistency and outperforms classical baselines.

Contribution

NSDD distills the null-space component of an iterative solver into a single-pass model, enabling fast, high-quality lensless image reconstruction without paired supervision.

Findings

NSDD achieves near-teacher perceptual quality.

NSDD is the second fastest method after Wiener.

NSDD outperforms DPS and classical convex baselines.

Abstract

State-of-the-art photorealistic reconstructions for lensless cameras often rely on paired lensless-lensed supervision, which can bias models due to lens-lensless domain mismatch. To avoid this, ground-truth-free diffusion priors are attractive; however, generic formulations tuned for conventional inverse problems often break under the noisy, highly multiplexed, and ill-posed lensless deconvolution setting. We observe that methods which separate range-space enforcement from null-space diffusion-prior updates yield stable, realistic reconstructions. Building on this, we introduce Null-Space Diffusion Distillation (NSDD): a single-pass student that distills the null-space component of an iterative DDNM+ solver, conditioned on the lensless measurement and on a range-space anchor. NSDD preserves measurement consistency and achieves photorealistic results without paired supervision at a fraction of the runtime and memory. On Lensless-FFHQ and PhlatCam, NSDD is the second fastest, behind Wiener, and achieves near-teacher perceptual quality (second-best LPIPS, below DDNM+), outperforming DPS and classical convex baselines. These results suggest a practical path toward fast, ground-truth-free, photorealistic lensless imaging.