MIAR reformulates super-resolution as a conditional and progressive next-scale prediction task through a multi-scale autoregressive framework that achieves a 7.86% improvement in the perceptual metric MUSIQ compared with the state of the art, while simultaneously delivering a 2.02x speedup over diffusion-based methods.
Abstract
Medical Image Super-Resolution (MISR) aims to enhance spatial resolution without requiring hardware modifications. Although deep learning has yielded promising results, existing paradigms face a critical trade-off: diffusion-based methods suffer from prohibitive inference latency and compromised structural fidelity, whereas regression-based models typically produce over-smoothed results that lack perceptual realism. To address these limitations, we propose MIAR, which reformulates super-resolution as a conditional and progressive next-scale prediction task through a multi-scale autoregressive framework. To ensure structural fidelity, we augment the autoregressive backbone with a Scale-Adaptive Structural Decoder. Furthermore, we integrate a hierarchical beam search strategy during inference to mitigate the recursive error accumulation inherent in autoregressive generation, a phenomenon that is especially pronounced in medical images. Extensive experiments demonstrate that MIAR establishes new state-of-the-art benchmarks while maintaining superior fidelity. Notably, our framework achieves a 7.86% improvement in the perceptual metric MUSIQ compared with the state of the art, while simultaneously delivering a 2.02x speedup over diffusion-based methods.
This work proposes a perceptually regularized diffusion framework that incorporates prior knowledge through perceptual-loss-based regularization, improving training convergence and encouraging the recovery of meaningful image features.
Chuxiang Wang, Pavithra Venkatachalapathy, Ying Liang et al.· 0 citations
This study introduces a novel 3D registration framework centered on a dynamic wavelet transform module that achieves superior registration fidelity, highlighting its potential for practical clinical implementation.
Bo-Hua Chu, Bao-Ju Zhang, Bo Zhang et al.· Interdisciplinary Sciences C...· 0 citations
Deep learning has achieved remarkable success in image super-resolution, producing visually convincing high-resolution results from low-resolution inputs. However, most existing methods are designed for fixed upscaling factors, limiting their flexibility and adaptability to arbitrary magnification scales. In this work,...
N. Vu· International Conference on...· 0 citations
Experimental results across several CT inverse problem settings show that Flow Matching-based approaches consistently outperform diffusion-based methods in terms of PSNR, SSIM, and perceptual quality, while requiring fewer sampling steps.
An efficient diffusion framework that jointly diffuses a baseline scan and its follow-up residual, summed to synthesize the follow-up scan, while concurrently predicting a spatial uncertainty map, in a single reverse diffusion process is proposed.
A. Oliveras, Roger Marí, Rafael Redondo et al.· arXiv.org· 1 citation
Super-resolution and quality enhancement of 1.5\,T brain MRI are normally validated with image-fidelity metrics, although their purpose is to improve downstream analysis. We study whether enhancement improves tissue segmentation, and for which segmenters. We propose an unpaired, physics-guided training pipeline for a l...
Kavitha Viswanathan, Harsh Choudhary, A. Sethi· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.