零空间扩散蒸馏解锁无透镜成像的速度、保真度和真实感
Null-Space Diffusion Distillation Unlocks Speed, Fidelity and Realism in Lensless Imaging
AI总结：
提出零空间扩散蒸馏（NSDD），通过将结构化扩散先验蒸馏为前馈网络，实现单次高质量重建，兼顾测量一致性、感知质量和推理速度。
摘要：
无透镜成像从高度复用的测量中重建场景，导致严重不适定的逆问题。在这项工作中，我们识别出无透镜重建范式在测量一致性、感知质量和推理速度之间的基本权衡。传统方法倾向于一致性但产生感知退化的结果，监督方法实现高质量重建和快速推理但可能违反物理约束，而扩散先验方法（特别是使用范围-零分解等结构化约束时）实现了高感知质量和一致性，但由于迭代采样仍然缓慢。基于这一观察，我们提出零空间扩散蒸馏（NSDD），一种单次重建模型，将结构化扩散先验推理蒸馏为高效的前馈网络。NSDD学习生成高质量重建，保持测量一致性，同时避免昂贵的迭代采样。实验结果表明，NSDD实现了与扩散先验方法相竞争的感知质量和一致性，同时提供显著更快的推理速度，并在所有三个目标之间实现了有利的平衡。此外，消融实验表明，蒸馏范围-零分解比非结构化全重建蒸馏提高了重建质量和鲁棒性，包括在未见过的真实场景上。这些结果凸显了结构感知蒸馏在高效无透镜成像中的潜力。代码见此 http URL。
英文摘要：
Lensless imaging reconstructs scenes from highly multiplexed measurements, resulting in a severely ill-posed inverse problem. In this work, we identify a fundamental trade-off between measurement consistency, perceptual quality, and inference speed across lensless reconstruction paradigms. Traditional methods favor consistency but produce perceptually degraded results, supervised approaches achieve high-quality reconstructions with fast inference but may violate physical constraints, and diffusion-prior methods achieve high perceptual quality and consistency--particularly when structured constraints such as range-null decomposition are used--but remain slow due to iterative sampling. Motivated by this observation, we propose Null-Space Diffusion Distillation (NSDD), a single-pass reconstruction model that distills structured diffusion-prior inference into an efficient feed-forward network. NSDD learns to produce high-quality reconstructions that preserve measurement consistency while avoiding costly iterative sampling. Experimental results demonstrate that NSDD achieves perceptual quality and consistency competitive with diffusion-prior methods, while providing significantly faster inference and offering a favorable balance across all three objectives. Furthermore, ablation experiments show that distilling the range--null decomposition improves reconstruction quality and robustness over unstructured full-reconstruction distillation, including on unseen real scenes. These results highlight the potential of structure-aware distillation for efficient lensless imaging. Code is available at github.com/JRCSAVSN/NullSpaceDiffusionDistillation.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
