Most of the recent generative image super-resolution (SR) methods rely on adapting large text-to-image (T2I) diffusion models pretrained on web-scale text-image data. While effective, this paradigm starts from a generic T2I generator, despite that SR is fundamentally a low-resolution (LR) input-conditioned image restoration task. In this work, we investigate whether an SR model trained purely on visual data can rival T2I-based ones. To this end, we propose VOSR, a Vision-Only generative framework for SR. We first extract semantically rich and spatially grounded features from the LR input using a pretrained vision encoder as visual semantic guidance. We then revisit classifier-free guidance for training generative models and show that the standard unconditional branch is ill-suited to restoration models trained from scratch. We therefore replace it with a restoration-oriented guidance strategy that preserves weak LR anchors. Built upon these designs, we first train a multi-step VOSR model from scratch and then distill it into a one-step model for efficient inference. VOSR requires less than one-tenth of the training cost of representative T2I-based SR methods, yet in both multi-step and one-step settings, it achieves competitive or even better perceptual quality and efficiency, while producing more faithful structures with fewer hallucinations on both synthetic and real-world benchmarks. Our results, for the first time, show that high-quality generative SR can be achieved without multimodal pretraining. The code and models can be found at https://github.com/cswry/VOSR.

翻译：近期大多数生成式图像超分辨率（SR）方法依赖于适配在大规模网络图文数据上预训练的文本到图像（T2I）扩散模型。尽管效果显著，但这一范式起始于通用型T2I生成器，而SR本质上是一项以低分辨率（LR）输入为条件的图像恢复任务。本文探究了纯粹在视觉数据上训练的SR模型是否能够与基于T2I的模型相抗衡。为此，我们提出了VOSR——一种仅基于视觉的SR生成框架。我们首先利用预训练的视觉编码器从LR输入中提取语义丰富且空间对齐的特征，作为视觉语义引导。随后，我们重新审视了用于训练生成模型的无分类器引导策略，发现标准的无条件分支并不适合从零训练的恢复模型。因此，我们将其替换为一种面向恢复的引导策略，该策略能够保留弱LR锚点。基于上述设计，我们首先从零训练一个多步VOSR模型，然后将其蒸馏为单步模型以实现高效推理。VOSR的训练成本不足代表性基于T2I的SR方法的十分之一，然而在多步和单步设置中，它在合成基准与真实世界基准上均实现了具有竞争力甚至更优的感知质量与效率，同时生成更忠实于输入的结构且幻觉更少。我们的结果首次证明，无需多模态预训练即可实现高质量生成式SR。代码与模型详见https://github.com/cswry/VOSR。