UGDiff introduces an uncertainty-guided diffusion paradigm for single-image super-resolution, aiming to improve the perception‑distortion trade‑off. The method estimates reconstruction uncertainty of latent features from a high‑fidelity image and uses this uncertainty, along with diffusion sampler posterior variance, to selectively restore high‑frequency details in uncertain regions while preserving fidelity elsewhere. Experiments show that UGDiff outperforms state‑of‑the‑art diffusion‑based SR methods.
By Ren Wang, Yung-Yu Chuang
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
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
Real-world image super-resolution (Real-ISR) aims to reconstruct high-quality (HQ) images from low-quality (LQ) inputs subject to diverse real-world degradations. Recent advances have leveraged the LQ inputs and natural image priors learned by Stable Diffusion models to achieve impressive results.
arXiv:2601.17723v3 Announce Type: replace
Abstract: Implicit neural representation (INR) has become the standard approach for arbitrary-scale image super-resolution (ASSR). However, no systematic emp...
By Tayyab Nasir, Daochang Liu, Ajmal Mian
arXiv:2609.30988v1 Announce Type: new
Abstract: Real-world image super-resolution (SR) requires recovering perceptually realistic high-resolution images from complex low-resolution observations while...
By Xin Di, Mingyu Shi, Yuanfei Bao, Long Peng, Yue Zhao, Jiaming Guo, Renjing Pei, Xueyang Fu, Yang Cao, Zheng-Jun Zha
SKILD is a scale‑invariant diffusion model that unifies image generation and continuous super‑resolution within a single unconditional framework. It achieves this by designing a forward process that progressively removes fine‑scale content while adding spectrum‑matched Gaussian noise, treating scale as an explicit diffusion coordinate. The same trained reverse process can generate images or perform super‑resolution simply by changing the starting timestep, yielding strong results on CIFAR‑10, ImageNet, and critical Ising models without task‑specific architecture or retraining.
By Zixin Jessie Chen, Zhuo Chen, Archer Wang, Jeff Gore, William T. Freeman, Congyue Deng, Marin Solja\v{c}i\'c
arXiv:2606. 30934v1 Announce Type: new Abstract: Modern text-to-image diffusion models, such as diffusion transformers (DiT), rely on timestep or prompt embeddings to modulate the strength of the denoising process in each timestep.
By Luke Budny, Yuhong Guo, Kevin Cheung
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
Diffusion transformer (DiT) research on image generation has converged to a single evaluation setup: class-conditional generation on ImageNet. While methods improve the FID and related metrics, it is increasingly unclear whether they reflect real progress in generative modeling.
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 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