Research
Progressively Texture-Aware Diffusion for Contrast-Enhanced Sparse-View CT
arXiv:2604.11559v1 Announce Type: new Abstract: Diffusion-based sparse-view CT (SVCT) imaging has achieved remarkable advancements in recent years, thanks to its more stable generative capability. How
arXiv:2604.11559v1 Announce Type: new 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 PTD_{extit{rec}} and a conditional diffusion module PTD_{extit{diff}}. PTD_{extit{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, PTD_{extit{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.
Related
- Vector Field Synthesis with Sparse Streamlines Using Diffusion Model
- Measurement-Consistent Langevin Corrector for Stabilizing Latent Diffusion Inverse Problem Solvers
- RectifiedHR: Enable Efficient High-Resolution Synthesis via Energy Rectification
- SVGFusion: A VAE-Diffusion Transformer for Vector Graphic Generation
Source: arXiv cs.CV | 2026-04-14