# Single-Image Depth from Defocus with Coded Aperture and Diffusion Posterior Sampling

arXiv: https://arxiv.org/abs/2509.17427 · HTML: https://mlsanity.com/paper/2509.17427/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models.
- Builds on 24 of its 45 references that are in the map.
- First posted on arXiv 22 Sep 2025.

## Placed in

- Diffusion models / [3D, point cloud and scene generation](https://mlsanity.com/diffusion/3d-point-cloud-and-scene-generation/)

## Builds on (most cited first, 24 of 24)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [Image Super-Resolution via Iterative Refinement](https://mlsanity.com/paper/2104.07636/) (2021)
- [Diffusion Posterior Sampling for General Noisy Inverse Problems](https://mlsanity.com/paper/2209.14687/) (2022)
- [Palette: Image-to-Image Diffusion Models](https://mlsanity.com/paper/2111.05826/) (2021)
- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [Solving Inverse Problems in Medical Imaging with Score-Based Generative Models](https://mlsanity.com/paper/2111.08005/) (2021)
- [Decomposed Diffusion Sampler for Accelerating Large-Scale Inverse Problems](https://mlsanity.com/paper/2303.05754/) (2023)
- [Noise2Score: Tweedie's Approach to Self-Supervised Image Denoising without Clean Images](https://mlsanity.com/paper/2106.07009/) (2021)
- [Parallel Diffusion Models of Operator and Image for Blind Inverse Problems](https://mlsanity.com/paper/2211.10656/) (2022)
- [Super-CLEVR: A Virtual Benchmark to Diagnose Domain Robustness in Visual Reasoning](https://mlsanity.com/paper/2212.00259/) (2022)
- [Prompt-tuning latent diffusion models for inverse problems](https://mlsanity.com/paper/2310.01110/) (2023)
- [Deep Optics for Monocular Depth Estimation and 3D Object Detection](https://mlsanity.com/paper/1904.08601/) (2019)
- [Single Image Depth Estimation Trained via Depth from Defocus Cues](https://mlsanity.com/paper/2001.05036/) (2020)
- [Single-shot Hyperspectral-Depth Imaging with Learned Diffractive Optics](https://mlsanity.com/paper/2009.00463/) (2020)
- [Untrained networks for compressive lensless photography](https://mlsanity.com/paper/2103.07609/) (2021)
- [Extended Depth-of-Field Lensless Imaging using an Optimized Radial Mask](https://mlsanity.com/paper/2303.11554/) (2023)

## Abstract (arXiv)

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.