AI RESEARCH
VARestorer: One-Step VAR Distillation for Real-World Image Super-Resolution
arXiv CS.LG
•
ArXi:2604.21450v1 Announce Type: cross Recent advancements in visual autoregressive models (VAR) have nstrated their effectiveness in image generation, highlighting their potential for real-world image super-resolution (Real-ISR). However, adapting VAR for ISR presents critical challenges. The next-scale prediction mechanism, constrained by causal attention, fails to fully exploit global low-quality (LQ) context, resulting in blurry and inconsistent high-quality (HQ) outputs. Additionally, error accumulation in the iterative prediction severely degrades coherence in ISR task.