OMGSR: You Only Need One Mid-timestep Guidance for Real-World Image Super-Resolution

• URL: http://arxiv.org/abs/2508.08227v1
• Date: Mon, 11 Aug 2025 17:44:59 GMT
• Title: OMGSR: You Only Need One Mid-timestep Guidance for Real-World Image Super-Resolution
• Abstract summary: One Mid-timestep Guidance Real-ISR (OMGSR) is a universal framework applicable to DDPM/FM-based generative models.<n>We instantiate OMGSR for DDPM/FM-based generative models with two variants: OMGSR-S (SD-Turbo) and OMGSR-F (FLUX.1-dev)
• Score: 20.816585773567677
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Denoising Diffusion Probabilistic Models (DDPM) and Flow Matching (FM) generative models show promising potential for one-step Real-World Image Super-Resolution (Real-ISR). Recent one-step Real-ISR models typically inject a Low-Quality (LQ) image latent distribution at the initial timestep. However, a fundamental gap exists between the LQ image latent distribution and the Gaussian noisy latent distribution, limiting the effective utilization of generative priors. We observe that the noisy latent distribution at DDPM/FM mid-timesteps aligns more closely with the LQ image latent distribution. Based on this insight, we present One Mid-timestep Guidance Real-ISR (OMGSR), a universal framework applicable to DDPM/FM-based generative models. OMGSR injects the LQ image latent distribution at a pre-computed mid-timestep, incorporating the proposed Latent Distribution Refinement loss to alleviate the latent distribution gap. We also design the Overlap-Chunked LPIPS/GAN loss to eliminate checkerboard artifacts in image generation. Within this framework, we instantiate OMGSR for DDPM/FM-based generative models with two variants: OMGSR-S (SD-Turbo) and OMGSR-F (FLUX.1-dev). Experimental results demonstrate that OMGSR-S/F achieves balanced/excellent performance across quantitative and qualitative metrics at 512-resolution. Notably, OMGSR-F establishes overwhelming dominance in all reference metrics. We further train a 1k-resolution OMGSR-F to match the default resolution of FLUX.1-dev, which yields excellent results, especially in the details of the image generation. We also generate 2k-resolution images by the 1k-resolution OMGSR-F using our two-stage Tiled VAE & Diffusion.

Related papers

• DNF-SR: Dual-Input and Negative-Aware Feature Fine-Tuning for Real-World Image Super-Resolution [50.847827209157494]
  Unmediatedly feeding LR into a diffusion model creates a distributional gap with the model's original input.<n>We propose a Dual-input and Negative-aware Feature fine-tuning method for Real-ISR.<n>We exploit this property and propose a post-training optimization method, Negative-aware Feature Fine-Tuning (NF2T), which guides the model toward producing higher-quality results.
  arXiv  Detail & Related papers  (2026-09-14T06:53:22Z)
• RFMSR: Residual Flow Matching for Image Super-Resolution [43.28301144364581]
  Residual Flow Matching for Image Super-Resolution (RFMSR)<n>Phase I pretrains the velocity field via conditional flow matching, while Phase II applies end-to-end supervision to the single-step prediction.<n>RFMSR achieves comparable or even superior perceptual quality compared to state-of-the-art (SOTA) methods.
  arXiv  Detail & Related papers  (2026-07-14T13:19:36Z)
• Noise-Started One-Step Real-World Super-Resolution via LR-Conditioned SplitMeanFlow and GAN Refinement [32.05719533625606]
  We propose a noise-started one-step Real-ISR framework via LR-conditioned SplitMeanFlow and GAN refinement.<n> SMFSR achieves state-of-the-art quality among one-step diffusion-based Real-ISR methods while retaining fast single-step inference.
  arXiv  Detail & Related papers  (2026-05-10T05:01:32Z)
• Large Scale Diffusion Distillation via Score-Regularized Continuous-Time Consistency [60.74505433956616]
  continuous-time consistency model (sCM) is theoretically principled and empirically powerful for accelerating academic-scale diffusion.<n>We first develop a parallelism-compatible FlashAttention-2 JVP kernel, enabling sCM training on models with over 10 billion parameters and high-dimensional video tasks.<n>We propose the score-regularized continuous-time consistency model (rCM), which incorporates score distillation as a long-skip regularizer.
  arXiv  Detail & Related papers  (2025-10-09T16:45:30Z)
• One Diffusion Step to Real-World Super-Resolution via Flow Trajectory Distillation [60.54811860967658]
  FluxSR is a novel one-step diffusion Real-ISR based on flow matching models.<n>First, we introduce Flow Trajectory Distillation (FTD) to distill a multi-step flow matching model into a one-step Real-ISR.<n>Second, to improve image realism and address high-frequency artifact issues in generated images, we propose TV-LPIPS as a perceptual loss.
  arXiv  Detail & Related papers  (2025-02-04T04:11:29Z)
• One-step Diffusion with Distribution Matching Distillation [54.723565605974294]
  We introduce Distribution Matching Distillation (DMD), a procedure to transform a diffusion model into a one-step image generator. We enforce the one-step image generator match the diffusion model at distribution level, by minimizing an approximate KL divergence. Our method outperforms all published few-step diffusion approaches, reaching 2.62 FID on ImageNet 64x64 and 11.49 FID on zero-shot COCO-30k.
  arXiv  Detail & Related papers  (2023-11-30T18:59:20Z)
• LFSRDiff: Light Field Image Super-Resolution via Diffusion Models [18.20217829625834]
  Light field (LF) image super-resolution (SR) is a challenging problem due to its inherent ill-posed nature. mainstream LF image SR methods typically adopt a deterministic approach, generating only a single output supervised by pixel-wise loss functions. We introduce LFSRDiff, the first diffusion-based LF image SR model, by incorporating the LF disentanglement mechanism.
  arXiv  Detail & Related papers  (2023-11-27T07:31:12Z)
• Hierarchical Integration Diffusion Model for Realistic Image Deblurring [71.76410266003917]
  Diffusion models (DMs) have been introduced in image deblurring and exhibited promising performance. We propose the Hierarchical Integration Diffusion Model (HI-Diff), for realistic image deblurring. Experiments on synthetic and real-world blur datasets demonstrate that our HI-Diff outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-05-22T12:18:20Z)
• DiffBFR: Bootstrapping Diffusion Model Towards Blind Face Restoration [8.253458555695767]
  We propose DiffBFR to introduce Diffusion Probabilistic Model (DPM) for Blind Face Restoration (BFR) DPM avoids training collapse and generates long-tail distribution. It restores identity information from low-quality images and then enhances texture details according to distribution of real faces.
  arXiv  Detail & Related papers  (2023-05-08T07:22:37Z)
• DDFM: Denoising Diffusion Model for Multi-Modality Image Fusion [144.9653045465908]
  We propose a novel fusion algorithm based on the denoising diffusion probabilistic model (DDPM) Our approach yields promising fusion results in infrared-visible image fusion and medical image fusion.
  arXiv  Detail & Related papers  (2023-03-13T04:06:42Z)
• Diffusion Probabilistic Model Made Slim [128.2227518929644]
  We introduce a customized design for slim diffusion probabilistic models (DPM) for light-weight image synthesis. We achieve 8-18x computational complexity reduction as compared to the latent diffusion models on a series of conditional and unconditional image generation tasks.
  arXiv  Detail & Related papers  (2022-11-27T16:27:28Z)
• SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Models [19.17571465274627]
  Single image super-resolution (SISR) aims to reconstruct high-resolution (HR) images from the given low-resolution (LR) ones. We propose a novel single image super-resolution diffusion probabilistic model (SRDiff) SRDiff is optimized with a variant of the variational bound on the data likelihood and can provide diverse and realistic SR predictions.
  arXiv  Detail & Related papers  (2021-04-30T12:31:25Z)

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.