用扩散模型做深度估计，无需配对数据，适配多种相机。
Single-Image Depth from Defocus with Coded Aperture and Diffusion Posterior Sampling
- 用扩散模型当先验，替代传统手工设计的约束。
- 在不同噪声下均优于现有方法，深度重建更准更稳。
- 不依赖特定相机或配对数据，通用性强适合实际部署。
我们提出一种基于编码孔径成像的单张图像深度估计方法，用学习得到的扩散先验替代人工设计的先验，仅作为正则化使用。优化框架通过可微分前向模型保证测量一致性，并在去噪图像域中利用扩散先验引导解，相比经典优化方法具有更高的准确性和稳定性。与U-Net类回归器不同，该方法无需成对的模糊-RGBD训练数据，且训练不绑定特定相机配置。在综合仿真和原型相机上的实验表明，该方法在不同噪声水平下均能实现稳健的RGBD重建，优于U-Net基线和经典编码孔径DFD方法。
原文摘要 · Abstract (English)
We propose a single-snapshot depth-from-defocus (DFD) reconstruction method for coded-aperture imaging that replaces hand-crafted priors with a learned diffusion prior used purely as regularization. Our optimization framework enforces measurement consistency via a differentiable forward model while guiding solutions with the diffusion prior in the denoised image domain, yielding higher accuracy and stability than classical optimization. Unlike U-Net-style regressors, our approach requires no paired defocus-RGBD training data and does not tie training to a specific camera configuration. Experiments on comprehensive simulations and a prototype camera demonstrate consistently strong RGBD reconstructions across noise levels, outperforming both U-Net baselines and a classical coded-aperture DFD method.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。