The paper introduces $p$-Bridge, a unified diffusion framework for Tweedie noise that models sensor noise across Gaussian, Poisson, and Gamma regimes using a noise exponent $p$ and accumulated measurement $ u$. It defines a noise plane and a stochastic bridge that interprets denoising as progressive measurement accumulation, allowing restoration between arbitrary measurement levels. A single exponent-conditioned network learns a shared reverse-mean update and deviance-based objective, achieving cross-exponent robustness comparable to multiple specialist models and demonstrating effectiveness on synthetic images, fluorescence microscopy, and SAR data.
arXiv:2512. 23818v2 Announce Type: replace-cross Abstract: Denoising and score estimation are classically linked through Tweedie's formula, which relates the posterior mean under Gaussian noise to the Stein score of the noisy marginal.
The paper investigates learning a generative model for clean images from only noisy observations. It shows that Noise2Noise regression can learn posterior predictions at or above the training noise level, but to predict below that level a consistency constraint is required. The authors derive conditions under which this consistency uniquely determines the continuation to the clean image distribution and validate the approach on CIFAR-10, photon‑counting microscopy, and synthetic aperture radar data.
The paper introduces a physics‑driven, cross‑domain iterative framework for self‑supervised low‑dose CT denoising. It first uses a learned sinogram prior and the LDCT noise model to separate Poisson and Gaussian noise components, then applies binomial and Gaussian data thinning to create two training pairs with independent noise realizations. These pairs train an image‑domain network whose outputs are forward‑projected to refine the prior, yielding consistent performance gains over existing self‑supervised baselines and comparable results to supervised methods.
The paper proposes using the inherent shot‑noise from quantum measurements as a resource for diffusion models, replacing part of the stochastic noise normally injected during generation. By modeling measurement error as multinomial sampling noise and mapping the diffusion process onto a bounded hyperplane, the authors derive a state‑dependent adaptive shot budget that matches the mean and covariance of a shot‑noise‑free update. Experiments on an eight‑dimensional Gaussian mixture and MNIST latent diffusion demonstrate that this approach achieves comparable generation quality with dramatically fewer shots—down to 303 shots per sample versus 1.6 × 10⁶ in a high‑shot baseline.
arXiv:2606. 03393v1 Announce Type: new Abstract: We propose a novel diffusion model, Flicker-DDPM, which incorporates flicker (1/f) noise inspired by self-organized criticality (SOC), a widely observed phenomenon in natural systems.
arXiv:2602. 09639v2 Announce Type: replace Abstract: Denoising diffusion models (DDMs) are state-of-the-art methods for learning densities from data across numerous domains, yet many aspects of the training and sampling pipeline remain poorly understood.
arXiv:2606. 28513v1 Announce Type: cross Abstract: Positron emission tomography (PET) seeks to balance diagnostic quality with ra-diation dose.
arXiv:2610.34834v1 Announce Type: new Abstract: Clean-image prediction ($x$-prediction) and noise prediction yield equivalent population-optimal denoisers, yet can perform very differently in finite...
arXiv:2610.29102v1 Announce Type: new Abstract: Diffusion posterior samplers reconstruct signals by combining a pretrained diffusion prior with a measurement likelihood specified by a forward model a...
Diffusion posterior samplers reconstruct signals by combining a pretrained diffusion prior with a measurement likelihood specified by a forward model and a noise model. Calibration and reference data...
arXiv:2611.05843v1 Announce Type: cross Abstract: Existing generative model-based approaches to linear inverse problems typically use the acquired noisy measurement to condition or guide sampling in...
The paper proposes a new covariance model for Denoising Diffusion Probabilistic Models (DDPMs) that captures non‑diagonal correlations and the power‑law frequency spectrum of natural images. Using a Kronecker‑factored DCT (K‑DCT) decomposition, the authors reduce computational complexity from quadratic to log‑linear, enabling efficient sampling with few steps. Experiments on CIFAR‑10, Celeb‑A, ImageNet, and LSUN demonstrate improved FID and likelihoods over previous state‑of‑the‑art samplers.