English

Progressively Texture-Aware Diffusion for Contrast-Enhanced Sparse-View CT

Computer Vision and Pattern Recognition 2026-04-14 v1 Medical Physics

Abstract

Diffusion-based sparse-view CT (SVCT) imaging has achieved remarkable advancements in recent years, thanks to its more stable generative capability. However, recovering reliable image content and visually consistent textures is still a crucial challenge. In this paper, we present a Progressively Texture-aware Diffusion (PTD) model, a coarse-to-fine learning framework tailored for SVCT. Specifically, PTD comprises a basic reconstructive module PTDrec_{\textit{rec}} and a conditional diffusion module PTDdiff_{\textit{diff}}. PTDrec_{\textit{rec}} first learns a deterministic mapping to recover the majority of the underlying low-frequency signals (i.e., coarse content with smoothed textures), which serves as the initial estimation to enable fidelity. Moreover, PTDdiff_{\textit{diff}} aims to reconstruct high-fidelity details for coarse prediction, which explores a dual-domain guided conditional diffusion to generate reliable and consistent textures. Extensive experiments on sparse-view CT reconstruction demonstrate that our PTD achieves superior performance in terms of structure similarity and visual appeal with only a few sampling steps, which mitigates the randomness inherent in general diffusion models and enables a better trade-off between visual quality and fidelity of high-frequency details.

Keywords

Cite

@article{arxiv.2604.11559,
  title  = {Progressively Texture-Aware Diffusion for Contrast-Enhanced Sparse-View CT},
  author = {Tianqi Wang and Wenchao Du and Hongyu Yang},
  journal= {arXiv preprint arXiv:2604.11559},
  year   = {2026}
}

Comments

ICASSP2026

R2 v1 2026-07-01T12:06:36.320Z