VOSR: A Vision-Only Generative Model for Image Super-Resolution

• URL: http://arxiv.org/abs/2604.03225v1
• Date: Fri, 03 Apr 2026 17:50:29 GMT
• Title: VOSR: A Vision-Only Generative Model for Image Super-Resolution
• Abstract summary: We propose a Vision-Only generative framework for generative image super-resolution (SR)<n>We first extract semantically rich and spatially grounded features from the LR input using a pretrained vision encoder as visual semantic guidance.<n>Our results, for the first time, show that high-quality generative SR can be achieved without multimodal pretraining.
• Score: 28.65862989487937
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Hierarchical Image Tokenization for Multi-Scale Image Super Resolution [47.66856101347057]
  We introduce a multi-scale Image Super Resolution (ISR) method building on recent advances in Visual Auto-Regressive ( VAR) modeling.<n>We introduce two novel components to the VAR training for ISR, aiming at increasing its flexibility and reducing its complexity.<n>Our proposed HIT acts as a strong inductive bias for the VAR training, resulting in a small model that achieves state-of-the-art results without external training data.
  arXiv  Detail & Related papers  (2026-05-14T14:35:51Z)
• VARestorer: One-Step VAR Distillation for Real-World Image Super-Resolution [76.19751531910039]
  We propose VARestorer, a framework that transforms a pre-trained text-to-image VAR model into a one-step ISR model.<n>VARestorer achieves state-of-the-art performance with 72.32 MUSIQ and 0.7669 CLIPIQA on DIV2K dataset.
  arXiv  Detail & Related papers  (2026-04-23T09:09:36Z)
• Dual-domain Adaptation Networks for Realistic Image Super-resolution [81.34345637776408]
  Realistic image super-resolution (SR) focuses on transforming real-world low-resolution (LR) images into high-resolution (HR) ones.<n>Current methods struggle with limited real-world LR-HR data, impacting the learning of basic image features.<n>We introduce a novel approach, which is able to efficiently adapt pre-trained image SR models from simulated to real-world datasets.
  arXiv  Detail & Related papers  (2025-11-21T12:57:23Z)
• NSARM: Next-Scale Autoregressive Modeling for Robust Real-World Image Super-Resolution [17.72407853450265]
  We introduce a robust Real-ISR framework, namely Next-Scale Autoregressive Modeling (NSARM)<n>As a pure AR model, NSARM achieves superior visual results over existing Real-ISR methods while maintaining a fast inference speed.
  arXiv  Detail & Related papers  (2025-10-01T12:29:58Z)
• Multi-scale Image Super Resolution with a Single Auto-Regressive Model [40.77470215283583]
  We tackle Image Super Resolution (ISR) using recent advances in Visual Auto-Regressive ( VAR) modeling.<n>To the best of our knowledge, this is the first time a quantizer is trained to force semantically consistent residuals at different scales.<n>Our model can denoise the LR image and super-resolve at half and full target upscale factors in a single forward pass.
  arXiv  Detail & Related papers  (2025-06-05T13:02:23Z)
• A Lightweight Image Super-Resolution Transformer Trained on Low-Resolution Images Only [22.127873567034825]
  Transformer architectures prominently lead single-image super-resolution (SISR) benchmarks, reconstructing high-resolution (HR) images from their low-resolution (LR) counterparts.<n>Their strong representative power, however, comes with a higher demand for training data compared to convolutional neural networks (CNNs)<n>In this work, we are the first to utilize a lightweight vision transformer model with LR-only training methods addressing the unsupervised SISR LR-only benchmark.
  arXiv  Detail & Related papers  (2025-03-30T00:52:26Z)
• AdaptSR: Low-Rank Adaptation for Efficient and Scalable Real-World Super-Resolution [50.584551250242235]
  AdaptSR is a low-rank adaptation framework that efficiently repurposes bi-cubic-trained SR models for real-world tasks.<n>Our experiments demonstrate that AdaptSR outperforms GAN and diffusion-based SR methods by up to 4 dB in PSNR and 2% in perceptual scores on real SR benchmarks.
  arXiv  Detail & Related papers  (2025-03-10T18:03:18Z)
• Efficient Test-Time Adaptation for Super-Resolution with Second-Order Degradation and Reconstruction [62.955327005837475]
  Image super-resolution (SR) aims to learn a mapping from low-resolution (LR) to high-resolution (HR) using paired HR-LR training images. We present an efficient test-time adaptation framework for SR, named SRTTA, which is able to quickly adapt SR models to test domains with different/unknown degradation types.
  arXiv  Detail & Related papers  (2023-10-29T13:58:57Z)
• S2R: Exploring a Double-Win Transformer-Based Framework for Ideal and Blind Super-Resolution [5.617008573997855]
  A light-weight transformer-based SR model (S2R transformer) and a novel coarse-to-fine training strategy are proposed. The proposed S2R outperforms other single-image SR models in ideal SR condition with only 578K parameters. It can achieve better visual results than regular blind SR models in blind fuzzy conditions with only 10 gradient updates.
  arXiv  Detail & Related papers  (2023-08-16T04:27:44Z)
• LAPAR: Linearly-Assembled Pixel-Adaptive Regression Network for Single Image Super-Resolution and Beyond [75.37541439447314]
  Single image super-resolution (SISR) deals with a fundamental problem of upsampling a low-resolution (LR) image to its high-resolution (HR) version. This paper proposes a linearly-assembled pixel-adaptive regression network (LAPAR) to strike a sweet spot of deep model complexity and resulting SISR quality.
  arXiv  Detail & Related papers  (2021-05-21T15:47:18Z)
• DDet: Dual-path Dynamic Enhancement Network for Real-World Image Super-Resolution [69.2432352477966]
  Real image super-resolution(Real-SR) focus on the relationship between real-world high-resolution(HR) and low-resolution(LR) image. In this article, we propose a Dual-path Dynamic Enhancement Network(DDet) for Real-SR. Unlike conventional methods which stack up massive convolutional blocks for feature representation, we introduce a content-aware framework to study non-inherently aligned image pair.
  arXiv  Detail & Related papers  (2020-02-25T18:24:51Z)
• Characteristic Regularisation for Super-Resolving Face Images [81.84939112201377]
  Existing facial image super-resolution (SR) methods focus mostly on improving artificially down-sampled low-resolution (LR) imagery. Previous unsupervised domain adaptation (UDA) methods address this issue by training a model using unpaired genuine LR and HR data. This renders the model overstretched with two tasks: consistifying the visual characteristics and enhancing the image resolution. We formulate a method that joins the advantages of conventional SR and UDA models.
  arXiv  Detail & Related papers  (2019-12-30T16:27:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.