Training-free, Perceptually Consistent Low-Resolution Previews with High-Resolution Image for Efficient Workflows of Diffusion Models

• URL: http://arxiv.org/abs/2604.09227v1
• Date: Fri, 10 Apr 2026 11:36:55 GMT
• Title: Training-free, Perceptually Consistent Low-Resolution Previews with High-Resolution Image for Efficient Workflows of Diffusion Models
• Abstract summary: We propose a method to generate high-fidelity LR images that are perceptually consistent with their HR counterparts.<n>Our method can generate LR images with up to 33% reduction while maintaining HR perceptual consistency.<n>Our formulation can be extended to image manipulations, such as warping and translation, demonstrating its generalizability.
• Score: 29.845476457607614
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Image generative models have become indispensable tools to yield exquisite high-resolution (HR) images for everyone, ranging from general users to professional designers. However, a desired outcome often requires generating a large number of HR images with different prompts and seeds, resulting in high computational cost for both users and service providers. Generating low-resolution (LR) images first could alleviate computational burden, but it is not straightforward how to generate LR images that are perceptually consistent with their HR counterparts. Here, we consider the task of generating high-fidelity LR images, called Previews, that preserve perceptual similarity of their HR counterparts for an efficient workflow, allowing users to identify promising candidates before generating the final HR image. We propose the commutator-zero condition to ensure the LR-HR perceptual consistency for flow matching models, leading to the proposed training-free solution with downsampling matrix selection and commutator-zero guidance. Extensive experiments show that our method can generate LR images with up to 33\% computation reduction while maintaining HR perceptual consistency. When combined with existing acceleration techniques, our method achieves up to 3$\times$ speedup. Moreover, our formulation can be extended to image manipulations, such as warping and translation, demonstrating its generalizability.

Related papers

• Fast Image Super-Resolution via Consistency Rectified Flow [65.54302099728712]
  Diffusion models (DMs) have demonstrated remarkable success in real-world image super-resolution (SR)<n>Recent efforts have introduced few- or single-step solutions, but existing methods inefficiently model the process from noisy input.<n>We propose FlowSR, a novel approach that reformulates the SR problem as a rectified flow from low-resolution (LR) to high-resolution (HR) images.
  arXiv  Detail & Related papers  (2026-05-12T16:42:38Z)
• Blind Super Resolution with Reference Images and Implicit Degradation Representation [5.34372866210952]
  Degradation kernels should account for not only the degradation process but also the downscaling factor.<n>Applying the same degradation kernel across varying super-resolution scales may be impractical.<n>Our research acknowledges degradation kernels and scaling factors as pivotal elements for the BSR task.
  arXiv  Detail & Related papers  (2025-07-18T13:45:04Z)
• Real-time 6K Image Rescaling with Rate-distortion Optimization [53.61374658914277]
  We propose a novel framework for real-time 6K rate-distortion-aware image rescaling. Our framework embeds an HR image into a JPEG LR thumbnail by an encoder. Then, an efficient frequency-aware decoder reconstructs a high-fidelity HR image from the LR one in real time.
  arXiv  Detail & Related papers  (2023-04-03T15:21:56Z)
• SRTGAN: Triplet Loss based Generative Adversarial Network for Real-World Super-Resolution [13.897062992922029]
  An alternative solution called Single Image Super-Resolution (SISR) is a software-driven approach that aims to take a Low-Resolution (LR) image and obtain the HR image. We introduce a new triplet-based adversarial loss function that exploits the information provided in the LR image by using it as a negative sample. We propose to fuse the adversarial loss, content loss, perceptual loss, and quality loss to obtain Super-Resolution (SR) image with high perceptual fidelity.
  arXiv  Detail & Related papers  (2022-11-22T11:17:07Z)
• Memory-augmented Deep Unfolding Network for Guided Image Super-resolution [67.83489239124557]
  Guided image super-resolution (GISR) aims to obtain a high-resolution (HR) target image by enhancing the spatial resolution of a low-resolution (LR) target image under the guidance of a HR image. Previous model-based methods mainly takes the entire image as a whole, and assume the prior distribution between the HR target image and the HR guidance image. We propose a maximal a posterior (MAP) estimation model for GISR with two types of prior on the HR target image.
  arXiv  Detail & Related papers  (2022-02-12T15:37:13Z)
• Learning Multiple Probabilistic Degradation Generators for Unsupervised Real World Image Super Resolution [5.987801889633082]
  Unsupervised real world super resolution aims at restoring high-resolution (HR) images given low-resolution (LR) inputs when paired data is unavailable. One of the most common approaches is synthesizing noisy LR images using GANs and utilizing a synthetic dataset to train the model in a supervised manner. We propose a probabilistic degradation generator to approximate the distribution of LR images given a HR image.
  arXiv  Detail & Related papers  (2022-01-26T04:49:11Z)
• 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)
• Best-Buddy GANs for Highly Detailed Image Super-Resolution [71.13466303340192]
  We consider the single image super-resolution (SISR) problem, where a high-resolution (HR) image is generated based on a low-resolution (LR) input. Most methods along this line rely on a predefined single-LR-single-HR mapping, which is not flexible enough for the SISR task. We propose best-buddy GANs (Beby-GAN) for rich-detail SISR. Relaxing the immutable one-to-one constraint, we allow the estimated patches to dynamically seek the best supervision.
  arXiv  Detail & Related papers  (2021-03-29T02:58:27Z)
• Deep Generative Adversarial Residual Convolutional Networks for Real-World Super-Resolution [31.934084942626257]
  We propose a deep Super-Resolution Residual Convolutional Generative Adversarial Network (SRResCGAN) It follows the real-world degradation settings by adversarial training the model with pixel-wise supervision in the HR domain from its generated LR counterpart. The proposed network exploits the residual learning by minimizing the energy-based objective function with powerful image regularization and convex optimization techniques.
  arXiv  Detail & Related papers  (2020-05-03T00:12:38Z)
• Closed-loop Matters: Dual Regression Networks for Single Image Super-Resolution [73.86924594746884]
  Deep neural networks have exhibited promising performance in image super-resolution. These networks learn a nonlinear mapping function from low-resolution (LR) images to high-resolution (HR) images. We propose a dual regression scheme by introducing an additional constraint on LR data to reduce the space of the possible functions.
  arXiv  Detail & Related papers  (2020-03-16T04:23:42Z)
• PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models [77.32079593577821]
  PULSE (Photo Upsampling via Latent Space Exploration) generates high-resolution, realistic images at resolutions previously unseen in the literature. Our method outperforms state-of-the-art methods in perceptual quality at higher resolutions and scale factors than previously possible.
  arXiv  Detail & Related papers  (2020-03-08T16:44:31Z)

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.