arXiv Machine Learning July 1, 2026 By Onkar Jadhav, Tim French, Matthew Rayson, Nicole L. Jones

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

Read the original on arXiv Machine Learning →

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.

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 Machine Learning.

arXiv Computer Vision

Aug 27

Uncertainty-Guided Latent Diffusion Models for Faithful Super Resolution

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

diffusion benchmarks

arXiv Machine Learning

Jul 7

Variational Sparse Paired Autoencoders (vsPAIR) for Inverse Problems and Uncertainty Quantification

arXiv:2602. 02948v3 Announce Type: replace Abstract: Inverse problems are fundamental to many scientific and engineering disciplines; they arise when one seeks to reconstruct hidden, underlying quantities from noisy measurements.

By Jack Michael Solomon, Rishi Leburu, Matthias Chung

safety

arXiv Machine Learning

Aug 6

PSI3D: Plug-and-Play 3D Stochastic Inference with Slice-wise Latent Diffusion Prior

arXiv:2512. 18367v2 Announce Type: replace-cross Abstract: Diffusion models are highly expressive image priors for Bayesian inverse problems.

By Wenhan Guo, Jinglun Yu, Yaning Wang, Jin U. Kang, Yu Sun

diffusion

arXiv Machine Learning

Jun 2

DVD: Discrete Voxel Diffusion for 3D Generation and Editing

arXiv:2605. 07971v2 Announce Type: replace-cross Abstract: We introduce Discrete Voxel Diffusion (DVD), a discrete diffusion framework to generate, assess, and edit sparse voxels for SLat (Structured LATent) based 3D generative pipelines.

By Zhengrui Xiang, Jiaqi Wu, Fupeng Sun, Heliang Zheng, Yingzhen Li

diffusion fine-tuning

arXiv Computer Vision

Sep 22

PixelDiT2: Representation-Grounded Pixel Diffusion Transformers

arXiv:2609.24919v1 Announce Type: new Abstract: Recent advances in pixel-space diffusion models have narrowed the image quality gap with latent-space diffusion, but still converge more slowly and lag...

By Yongsheng Yu, Wei Xiong, Yichen Sheng, Shiqiu Liu, Jiebo Luo

llms diffusion

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

One email a morning, machine-written

Related stories

Uncertainty-Guided Latent Diffusion Models for Faithful Super Resolution

Variational Sparse Paired Autoencoders (vsPAIR) for Inverse Problems and Uncertainty Quantification

PSI3D: Plug-and-Play 3D Stochastic Inference with Slice-wise Latent Diffusion Prior

DVD: Discrete Voxel Diffusion for 3D Generation and Editing

PixelDiT2: Representation-Grounded Pixel Diffusion Transformers

Perceptually Regularized Diffusion Model for Image Super-Resolution