Null-Space Diffusion Distillation for Efficient Photorealistic Lensless Imaging
This work addresses the domain mismatch issue in lensless imaging for applications requiring efficient and realistic reconstructions without ground-truth data, representing a strong specific gain.
The paper tackled the problem of photorealistic reconstructions for lensless cameras by introducing Null-Space Diffusion Distillation (NSDD), which avoids paired supervision and achieves near-teacher perceptual quality with second-best LPIPS scores and is the second fastest method behind Wiener.
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.