PulseAugur
LIVE 08:29:53
research · [4 sources] ·
0
research

Diffusion models enhance image reconstruction for inverse problems and sparse-view CT

By PulseAugur Editorial · Summary by gemini-2.5-flash-lite from 4 sources

Researchers are developing new methods to improve image reconstruction from limited data using diffusion models. One approach optimizes diffusion priors from a single observation by combining existing models, showing promise in applications like black hole imaging. Another technique, Conditional Diffusion Posterior Alignment (CDPA), enables scalable 3D sparse-view CT reconstruction by conditioning a 2D diffusion model on an initial 3D reconstruction and aligning it with measured projections. A third method, DiffNR, enhances neural representations for sparse-view CT by using a diffusion model called SliceFixer to correct artifacts and provide auxiliary supervision, leading to improved reconstruction quality and efficiency. AI

Summary written by gemini-2.5-flash-lite from 4 sources. How we write summaries →

IMPACT Advances in diffusion model optimization for limited-data image reconstruction could improve accuracy in medical imaging and scientific observation.

RANK_REASON The cluster contains multiple arXiv preprints detailing novel research in image reconstruction using diffusion models.

Read on arXiv cs.CV →

Diffusion models enhance image reconstruction for inverse problems and sparse-view CT

COVERAGE [4]

  1. arXiv cs.LG TIER_1 · Jonathan Patsenker, Henry Li, Myeongseob Ko, Ruoxi Jia, Yuval Kluger ·

    Injecting Measurement Information Yields a Fast and Noise-Robust Diffusion-Based Inverse Problem Solver

    arXiv:2508.02964v3 Announce Type: replace Abstract: Diffusion models have been firmly established as principled zero-shot solvers for linear and nonlinear inverse problems, owing to their powerful image prior and iterative sampling algorithm. These approaches often rely on Tweedi…

  2. arXiv cs.CV TIER_1 · Frederic Wang, Katherine L. Bouman ·

    Optimizing Diffusion Priors in Image Reconstruction from a Single Observation

    arXiv:2604.21066v2 Announce Type: replace Abstract: While diffusion priors generate high-quality posterior samples across many inverse problems, they are often trained on limited training sets or purely simulated data, thus inheriting the errors and biases of these underlying sou…

  3. arXiv cs.CV TIER_1 · Luis Barba, Johannes Kirschner, Benjamin Bejar ·

    Conditional Diffusion Posterior Alignment for Sparse-View CT Reconstruction

    arXiv:2604.21960v1 Announce Type: cross Abstract: Computed Tomography (CT) is a widely used imaging modality in medical and industrial applications. To limit radiation exposure and measurement time, there is a growing interest in sparse-view CT, where the number of projection vie…

  4. arXiv cs.CV TIER_1 · Xuelian Cheng ·

    DiffNR: Diffusion-Enhanced Neural Representation Optimization for Sparse-View 3D Tomographic Reconstruction

    Neural representations (NRs), such as neural fields and 3D Gaussians, effectively model volumetric data in computed tomography (CT) but suffer from severe artifacts under sparse-view settings. To address this, we propose DiffNR, a novel framework that enhances NR optimization wit…

RELATED ENTITIES

RELATED TOPICS