The paper revisits pixel-space diffusion models, showing that a vanilla diffusion transformer can generate directly in pixel space by swapping velocity prediction for clean image prediction. It introduces MFlow, an adaptive parameterization that interpolates between these two prediction modes based on data representation and model capacity, and demonstrates competitive performance on ImageNet, UCF‑101, and text‑to‑image tasks. Additionally, the authors add ConvRefiner, a lightweight convolutional module trained post‑hoc to restore high‑frequency details while preserving FID.
By Soumik Mukhopadhyay, Long Mai, Abhinav Shrivastava, Aniruddha Mahapatra
arXiv:2607. 15711v1 Announce Type: cross Abstract: Diffusion-based methods have achieved impressive performance in real-world image super-resolution (Real-ISR) by leveraging large pre-trained stable diffusion (SD) models as powerful generative priors.
By Xue Wu, Kang Zhao, Kafeng Wang, Jianfei Chen, Jingwei Xin, Nannan Wang, Xinbo Gao
arXiv:2608. 09133v1 Announce Type: cross Abstract: Image super-resolution (SR) with large generative models has recently achieved remarkable perceptual quality, yet maintaining fidelity to the LR observation remains challenging.
By Yu Shi, Yuyao Zhang, Yu-wing Tai
The paper introduces a perceptually regularized diffusion framework for image super‑resolution, adding perceptual‑loss based regularization to the standard diffusion training objective. This approach incorporates prior knowledge to improve training convergence and encourages the recovery of meaningful image features. Experiments on benchmark datasets show enhanced perceptual quality while maintaining competitive distortion metrics.
By Chuxiangbo Wang, Pavithra Venkatachalapathy, Ying Liang, Min Wang, Jing Qin, Yifei Lou, Weihong Guo
Consistent Distribution Matching is a data‑free distillation technique that accelerates diffusion and flow models by unifying sample generation and score estimation in a single student network. The method requires only a frozen teacher and a trainable student, optimizing a single objective that provably leads to Wasserstein convergence of the student’s flow‑map to the teacher’s marginals. On ImageNet 256×256, it achieves an FID of 2.04 with one function evaluation and 1.37 with four evaluations after just 40 training epochs, outperforming existing data‑free baselines.
By Yuxiang Fu, Qi Yan, Zike Wu, Yongxing Zhang, Purang Abolmaesumi, Lele Wang, Renjie Liao
Flow and diffusion models suffer from slow inference due to computationally expensive numerical integration. Distillation provides a promising way for a student model to learn from a teacher's dynamic...
The paper introduces SMFSR, a one‑step real‑world super‑resolution framework that retains the noise‑started generation of diffusion models while conditioning on low‑resolution images. It uses LR‑conditioned SplitMeanFlow with Interval Splitting Consistency to collapse a multi‑step trajectory into a single average‑velocity prediction, and adds a GAN refinement stage with a DINOv3 discriminator and variational score distillation to enhance texture realism. Experiments show SMFSR achieves state‑of‑the‑art perceptual quality among one‑step diffusion‑based methods while maintaining fast inference.
By Wei Zhu, Kai Zhang, Yu Zheng, Lei Luo, Yong Guo, Jian Yang
arXiv:2609.15120v1 Announce Type: new
Abstract: Benefiting from the powerful generative priors of diffusion models, diffusion-based real-world image super-resolution (Real-ISR) methods have demonstra...
By Shuhao Han, Wenjie Liao, Hayden Vance, Hang Dong, Rui Zhang, Chun-Le Guo, Chongyi Li
Recent advances in diffusion models have shown impressive performance in controllable image generation and dense prediction tasks. However, existing approaches typically treat diffusion-based controllable generation and dense prediction as separate tasks, overlooking the potential benefits of jointly modeling the heterogeneous distributions.
MOSAIC is an object‑centric framework that adapts pretrained diffusion Transformers for image restoration by learning compact structural conditions. It organizes degraded images into structural slots capturing object‑level and layout‑level evidence, integrates these across resolutions, and retrieves recurring priors from a shared prototype memory. Injecting these representations into selected layers of a frozen diffusion Transformer via lightweight residual modulation preserves the pretrained generative prior, yielding improved remote sensing image super‑resolution performance on UCMerced, AID, and RSSCN7 datasets.
By Liuqian Wang, Hanyu Xie, Rongzhen Zhao, Qi Ming, Chunjie Ma, Wentao Chao, Yufei Gao, Chengming Liu, Lei Shi
Unified image restoration (UIR) aims to recover high-quality (HQ) content from low-quality (LQ) images with different degradations using a single model. Most recent methods adapt large pretrained text-to-image (T2I) latent diffusion models for their strong capacity and generative priors.
The paper introduces a high‑resolution Rectified Flow Matching model trained on 256×256 chest CT images to serve as a generative prior for CT reconstruction. A two‑stage training strategy—initial strong anatomically informed augmentation followed by fine‑tuning—helps mitigate overfitting and improve structural fidelity. When evaluated on various CT inverse problems, Flow Matching‑based reconstruction methods outperform diffusion‑based algorithms in PSNR, SSIM, and perceptual quality while requiring fewer sampling steps.
By Davide Evangelista