Single-Image Depth from Defocus with Coded Aperture and Diffusion Posterior Sampling
On the map: Diffusion models → 3D, point cloud and scene generation
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.
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.
Builds on
24 of 45 references.
References · 24
- 2020Denoising Diffusion Probabilistic Modelscited by 21,076
- 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
- 2020Denoising Diffusion Implicit Modelscited by 9,781
- 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
- 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
- 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
- 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
- 2022Classifier-Free Diffusion Guidancecited by 5,847
- 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,614
- 2021Image Super-Resolution via Iterative Refinementcited by 1,511
- 2022Diffusion Posterior Sampling for General Noisy Inverse Problemscited by 1,416
- 2021Palette: Image-to-Image Diffusion Modelscited by 1,300
12 more
- 2017Deep Image Priorcited by 1,098
- 2021Solving Inverse Problems in Medical Imaging with Score-Based Generative Modelscited by 521
- 2023Decomposed Diffusion Sampler for Accelerating Large-Scale Inverse Problemscited by 132
- 2021Noise2Score: Tweedie's Approach to Self-Supervised Image Denoising without Clean Imagescited by 113
- 2022Parallel Diffusion Models of Operator and Image for Blind Inverse Problemscited by 113
- 2022Super-CLEVR: A Virtual Benchmark to Diagnose Domain Robustness in Visual Reasoningcited by 92
- 2023Prompt-tuning latent diffusion models for inverse problemscited by 70
- 2019Deep Optics for Monocular Depth Estimation and 3D Object Detectioncited by 65
- 2020Single Image Depth Estimation Trained via Depth from Defocus Cuescited by 45
- 2020Single-shot Hyperspectral-Depth Imaging with Learned Diffractive Opticscited by 39
- 2021Untrained networks for compressive lensless photographycited by 13
- 2023Extended Depth-of-Field Lensless Imaging using an Optimized Radial Maskcited by 2
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2024DifuzCam: Replacing Camera Lens with a Mask and a Diffusion Model
- 2026Robust Depth Super-Resolution via Adaptive Diffusion Sampling
- 2025Fine-grained Defocus Blur Control for Generative Image Models
- 2025Null-Space Diffusion Distillation Unlocks Speed, Fidelity and Realism in Lensless Imaging
- 2026EagleDepth: Efficient Fine-Grained Depth Estimation via Pixel Diffusion Decoder
- 2026U-DAVI: Uncertainty-Aware Diffusion-Prior-Based Amortized Variational Inference for Image Reconstruction
- 2025DiffCamera: Arbitrary Refocusing on Images
- 2024Marigold-DC: Zero-Shot Monocular Depth Completion with Guided Diffusion