arXiv Computer Vision August 27, 2026 By Ren Wang, Yung-Yu Chuang

Uncertainty-Guided Latent Diffusion Models for Faithful Super Resolution

Read the original on arXiv Computer Vision →

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

arXiv Machine Learning

Sep 3

Perceptually Regularized Diffusion Model for Image Super-Resolution

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

diffusion benchmarks

arXiv AI

Aug 11

When Latents Forget Pixels: Restoring Fidelity in Diffusion Transformer Super-Resolution

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

llms diffusion

arXiv Computer Vision

Sep 15

DNF-SR: Dual-Input and Negative-Aware Feature Fine-Tuning for Real-World Image Super-Resolution

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

diffusion fine-tuning

arXiv AI

Jul 20

Efficient Difficulty-Aware Dynamic Routing for Diffusion-Based Real-World Image Super-Resolution

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 benchmarks

arXiv Machine Learning

Jul 1

Patch-PODiff-ViT: Structured Latent Diffusion with Patchwise POD for Super-Resolution and Uncertainty Quantification

arXiv:2606. 31290v1 Announce Type: new Abstract: Diffusion models enable probabilistic super-resolution and conditional generation, but pixel-space methods are computationally expensive and learned latent spaces often lack interpretable uncertainty quantification.

By Onkar Jadhav, Tim French, Matthew Rayson, Nicole L. Jones

llms diffusion computer-vision

arXiv Computer Vision

Sep 1

PixelIR: Fidelity-Perception Decoupling via Pixel-Space Image-Residual Flow Matching for Efficient One-Step Real-World Super-Resolution

arXiv:2608.30782v1 Announce Type: new Abstract: Real-world image super-resolution (Real-ISR) aims to preserve structures supported by the degraded observation while reconstructing perceptually realis...

By Bingtian Qiao, Yue Shi, Yong Guo, Wenjun Zhang, Jiezhang Cao

diffusion