One-Step Diffusion-based Real-World Image Super-Resolution with Visual Perception Distillation

• URL: http://arxiv.org/abs/2506.02605v1
• Date: Tue, 03 Jun 2025 08:28:13 GMT
• Title: One-Step Diffusion-based Real-World Image Super-Resolution with Visual Perception Distillation
• Authors: Xue Wu, Jingwei Xin, Zhijun Tu, Jie Hu, Jie Li, Nannan Wang, Xinbo Gao,
• Abstract summary: We propose VPD-SR, a novel visual perception diffusion distillation framework specifically designed for image super-resolution (SR) generation.<n>VPD-SR consists of two components: Explicit Semantic-aware Supervision (ESS) and High-frequency Perception (HFP) loss.<n>The proposed VPD-SR achieves superior performance compared to both previous state-of-the-art methods and the teacher model with just one-step sampling.
• Score: 53.24542646616045
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Diffusion-based models have been widely used in various visual generation tasks, showing promising results in image super-resolution (SR), while typically being limited by dozens or even hundreds of sampling steps. Although existing methods aim to accelerate the inference speed of multi-step diffusion-based SR methods through knowledge distillation, their generated images exhibit insufficient semantic alignment with real images, resulting in suboptimal perceptual quality reconstruction, specifically reflected in the CLIPIQA score. These methods still have many challenges in perceptual quality and semantic fidelity. Based on the challenges, we propose VPD-SR, a novel visual perception diffusion distillation framework specifically designed for SR, aiming to construct an effective and efficient one-step SR model. Specifically, VPD-SR consists of two components: Explicit Semantic-aware Supervision (ESS) and High-Frequency Perception (HFP) loss. Firstly, the ESS leverages the powerful visual perceptual understanding capabilities of the CLIP model to extract explicit semantic supervision, thereby enhancing semantic consistency. Then, Considering that high-frequency information contributes to the visual perception quality of images, in addition to the vanilla distillation loss, the HFP loss guides the student model to restore the missing high-frequency details in degraded images that are critical for enhancing perceptual quality. Lastly, we expand VPD-SR in adversarial training manner to further enhance the authenticity of the generated content. Extensive experiments conducted on synthetic and real-world datasets demonstrate that the proposed VPD-SR achieves superior performance compared to both previous state-of-the-art methods and the teacher model with just one-step sampling.

Related papers

• GuideSR: Rethinking Guidance for One-Step High-Fidelity Diffusion-Based Super-Resolution [15.563111624900865]
  GuideSR is a novel single-step diffusion-based image super-resolution (SR) model specifically designed to enhance image fidelity.<n>Our approach consistently outperforms existing methods across various reference-based metrics including PSNR, SSIM, LPIPS, DISTS and FID.
  arXiv  Detail & Related papers  (2025-05-01T17:48:25Z)
• Quaternion Wavelet-Conditioned Diffusion Models for Image Super-Resolution [7.986370916847687]
  We introduce ResQu, a novel SR framework that integrates a quaternion wavelet preprocessing framework with latent diffusion models.<n>Our approach enhances the conditioning process by exploiting quaternion wavelet embeddings, which are dynamically integrated at different stages of denoising.<n>Our method achieves outstanding SR results, outperforming in many cases existing approaches in perceptual quality and standard evaluation metrics.
  arXiv  Detail & Related papers  (2025-05-01T06:17:33Z)
• One-Step Residual Shifting Diffusion for Image Super-Resolution via Distillation [90.84654430620971]
  Diffusion models for super-resolution (SR) produce high-quality visual results but require expensive computational costs.<n>We present RSD, a new distillation method for ResShift, one of the top diffusion-based SR models.<n>Our method is based on training the student network to produce such images that a new fake ResShift model trained on them will coincide with the teacher model.
  arXiv  Detail & Related papers  (2025-03-17T16:44:08Z)
• TSD-SR: One-Step Diffusion with Target Score Distillation for Real-World Image Super-Resolution [25.994093587158808]
  Pre-trained text-to-image diffusion models are increasingly applied to real-world image super-resolution (Real-ISR) tasks.<n>Given the iterative refinement nature of diffusion models, most existing approaches are computationally expensive.<n>We propose TSD-SR, a novel distillation framework specifically designed for real-world image super-resolution.
  arXiv  Detail & Related papers  (2024-11-27T12:01:08Z)
• Degradation-Guided One-Step Image Super-Resolution with Diffusion Priors [75.24313405671433]
  Diffusion-based image super-resolution (SR) methods have achieved remarkable success by leveraging large pre-trained text-to-image diffusion models as priors. We introduce a novel one-step SR model, which significantly addresses the efficiency issue of diffusion-based SR methods. Unlike existing fine-tuning strategies, we designed a degradation-guided Low-Rank Adaptation (LoRA) module specifically for SR.
  arXiv  Detail & Related papers  (2024-09-25T16:15:21Z)
• One Step Diffusion-based Super-Resolution with Time-Aware Distillation [60.262651082672235]
  Diffusion-based image super-resolution (SR) methods have shown promise in reconstructing high-resolution images with fine details from low-resolution counterparts. Recent techniques have been devised to enhance the sampling efficiency of diffusion-based SR models via knowledge distillation. We propose a time-aware diffusion distillation method, named TAD-SR, to accomplish effective and efficient image super-resolution.
  arXiv  Detail & Related papers  (2024-08-14T11:47:22Z)
• Learning from Multi-Perception Features for Real-Word Image Super-resolution [87.71135803794519]
  We propose a novel SR method called MPF-Net that leverages multiple perceptual features of input images. Our method incorporates a Multi-Perception Feature Extraction (MPFE) module to extract diverse perceptual information. We also introduce a contrastive regularization term (CR) that improves the model's learning capability.
  arXiv  Detail & Related papers  (2023-05-26T07:35:49Z)
• Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling [139.25215100378284]
  We propose a hierarchical conditional flow (HCFlow) as a unified framework for image SR and image rescaling. HCFlow learns a mapping between HR and LR image pairs by modelling the distribution of the LR image and the rest high-frequency component simultaneously. To further enhance the performance, other losses such as perceptual loss and GAN loss are combined with the commonly used negative log-likelihood loss in training.
  arXiv  Detail & Related papers  (2021-08-11T16:11:01Z)
• Boosting Image Super-Resolution Via Fusion of Complementary Information Captured by Multi-Modal Sensors [21.264746234523678]
  Image Super-Resolution (SR) provides a promising technique to enhance the image quality of low-resolution optical sensors. In this paper, we attempt to leverage complementary information from a low-cost channel (visible/depth) to boost image quality of an expensive channel (thermal) using fewer parameters.
  arXiv  Detail & Related papers  (2020-12-07T02:15:28Z)

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.