AlignVAR: Towards Globally Consistent Visual Autoregression for Image Super-Resolution

TL;DR

AlignVAR introduces a globally consistent autoregressive framework for image super-resolution, addressing local attention bias and residual supervision issues to improve structural coherence and efficiency.

Contribution

It proposes two novel components, SCA and HCC, to enhance global consistency and stability in visual autoregressive super-resolution models.

Findings

Improves structural coherence and perceptual fidelity.

Achieves over 10x faster inference than diffusion models.

Uses nearly 50% fewer parameters than leading approaches.

Abstract

Visual autoregressive (VAR) models have recently emerged as a promising alternative for image generation, offering stable training, non-iterative inference, and high-fidelity synthesis through next-scale prediction. This encourages the exploration of VAR for image super-resolution (ISR), yet its application remains underexplored and faces two critical challenges: locality-biased attention, which fragments spatial structures, and residual-only supervision, which accumulates errors across scales, severely compromises global consistency of reconstructed images. To address these issues, we propose AlignVAR, a globally consistent visual autoregressive framework tailored for ISR, featuring two key components: (1) Spatial Consistency Autoregression (SCA), which applies an adaptive mask to reweight attention toward structurally correlated regions, thereby mitigating excessive locality and enhancing long-range dependencies; and (2) Hierarchical Consistency Constraint (HCC), which augments residual learning with full reconstruction supervision at each scale, exposing accumulated deviations early and stabilizing the coarse-to-fine refinement process. Extensive experiments demonstrate that AlignVAR consistently enhances structural coherence and perceptual fidelity over existing generative methods, while delivering over 10x faster inference with nearly 50% fewer parameters than leading diffusion-based approaches, establishing a new paradigm for efficient ISR.