# NSARM: Next-Scale Autoregressive Modeling for Robust Real-World Image Super-Resolution

arXiv: https://arxiv.org/abs/2510.00820 · HTML: https://mlsanity.com/paper/2510.00820/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models.
- First posted on arXiv 1 Oct 2025.

## Placed in

- Diffusion models / [Inverse problems and image restoration](https://mlsanity.com/diffusion/inverse-problems-and-image-restoration/)

## Built on by (most cited first, 3 of 3)

- [Toward Real-world Infrared Image Super-Resolution: A Unified Autoregressive Framework and Benchmark Dataset](https://mlsanity.com/paper/2603.04745/) (2026)
- [Noise-Started One-Step Real-World Super-Resolution via LR-Conditioned SplitMeanFlow and GAN Refinement](https://mlsanity.com/paper/2605.09328/) (2026)
- [UHD Image Deblurring via Autoregressive Flow with Ill-conditioned Constraints](https://mlsanity.com/paper/2603.10517/) (2026)

## Abstract (arXiv)

Most recent real-world image super-resolution (Real-ISR) methods employ pre-trained text-to-image (T2I) diffusion models to synthesize the high-quality image either from random Gaussian noise, which yields realistic results but is slow due to iterative denoising, or directly from the input low-quality image, which is efficient but at the price of lower output quality. These approaches train ControlNet or LoRA modules while keeping the pre-trained model fixed, which often introduces over-enhanced artifacts and hallucinations, suffering from the robustness to inputs of varying degradations. Recent visual autoregressive (AR) models, such as pre-trained Infinity, can provide strong T2I generation capabilities while offering superior efficiency by using the bitwise next-scale prediction strategy. Building upon next-scale prediction, we introduce a robust Real-ISR framework, namely Next-Scale Autoregressive Modeling (NSARM). Specifically, we train NSARM in two stages: a transformation network is first trained to map the input low-quality image to preliminary scales, followed by an end-to-end full-model fine-tuning. Such a comprehensive fine-tuning enhances the robustness of NSARM in Real-ISR tasks without compromising its generative capability. Extensive quantitative and qualitative evaluations demonstrate that as a pure AR model, NSARM achieves superior visual results over existing Real-ISR methods while maintaining a fast inference speed. Most importantly, it demonstrates much higher robustness to the quality of input images, showing stronger generalization performance. Project page: https://github.com/Xiangtaokong/NSARM