arXiv Machine Learning

Hyperspectral Diffusion Equivariant Imaging (HyDiff-EI): A Self-supervised Framework for Hyperspectral Image Inpainting

The paper introduces HyDiff-EI, a self‑supervised framework that performs hyperspectral image inpainting using diffusion modeling without large‑scale pretraining. It learns directly from a single corrupted acquisition through test‑time optimization, incorporating equivariant consistency constraints that exploit the geometric symmetries of hyperspectral data. Experiments on real datasets such as Chikusei, Botswana, and EMIT show that HyDiff-EI achieves superior inpainting quality compared to existing self‑supervised and diffusion‑based methods, even under noisy conditions.

arXiv AI

Sep 1

EquiReg: Equivariance Regularized Diffusion for Inverse Problems

EquiReg introduces an equivariance‑regularized diffusion framework that penalises sampling trajectories deviating from the data manifold, thereby improving posterior sampling for inverse problems. By formalising manifold‑preferential equivariant functions—naturally arising from data augmentation or inherent symmetries—EquiReg guides diffusion steps toward symmetry‑preserving regions of the solution space. The method shows consistent gains in both linear and nonlinear image restoration tasks and partial differential equation solving, especially under reduced sampling and measurement consistency steps, and is available as open‑source code.

By Bahareh Tolooshams, Aditi Chandrashekar, Rayhan Zirvi, Abbas Mammadov, Jiachen Yao, Chuwei Wang, Anima Anandkumar

diffusion benchmarks

arXiv Computer Vision

4d ago

From Proper Scoring Rules and Edge Biases to Mumford-Shah Models: Robust Unsupervised Hyperspectral Image Segmentation

arXiv:2610.27958v1 Announce Type: new Abstract: Hyperspectral images provide a rich representation of the underlying spectrum for each pixel, allowing for a pixel-wise classification/segmentation int...

By Fabian Conrad, Benjamin Berkels

computer-vision benchmarks safety

arXiv Computer Vision

4d ago

Manifold Prior Guided Deep Unfolding for Hyperspectral Image Reconstruction

arXiv:2610.27874v1 Announce Type: new Abstract: Hyperspectral Image (HSI) reconstruction has made substantial progress with the deep unfolding framework by decomposing the problem into a projection m...

By Shuqi Liu, Yingkai Zhang, Lin Gu, Tao Zhang, Ying Fu

benchmarks safety

arXiv Computer Vision

Sep 7

Learning Spatial-Spectral Refinement and Calibrating Complementary Observations for Hyperspectral Image Super-Resolution

The paper introduces TSR-ITNR, a two‑stage, self‑supervised framework for hyperspectral image super‑resolution that fuses high‑resolution multispectral and low‑resolution hyperspectral data. Stage 1 refines an implicit Tucker representation using a low‑rank spatial tensor and spectral basis, enhanced by a pretrained denoiser, to capture fine spatial details and spectral correlations. Stage 2 applies parameter‑free calibration to extract complementary corrections from both observations, preserving geometry and ensuring orthogonal complementarity, leading to superior reconstruction quality demonstrated on benchmark datasets and improved downstream segmentation performance.

By Liqian Yang, Xingchi Chen, Xinfeng Gui, Xiangyong Cao, Qianxin Yi

computer-vision benchmarks

arXiv Machine Learning

Sep 10

Revisiting Spectral Representations in Generative Diffusion Models

arXiv:2609.08253v1 Announce Type: new Abstract: Diffusion models have shown remarkable performance on diverse generation tasks. Recent work finds that imposing representation alignment on the hidden...

By Yuehao Wang, Peihao Wang, Hanwen Jiang, Ziyi Yang, Qixing Huang, Zhangyang Wang

rag diffusion efficiency safety

arXiv Computer Vision

Oct 8

Toward Realistic Remote Sensing Dataset Distillation with Discriminative Prototype-guided Diffusion

arXiv:2601.15829v3 Announce Type: replace Abstract: Recent years have witnessed the remarkable success of deep learning in remote sensing image interpretation, driven by the availability of large-sca...

By Yonghao Xu, Pedram Ghamisi, Qihao Weng

diffusion efficiency benchmarks

arXiv Machine Learning

Jul 7

SE-UNet: Singular Equivariant Imaging for Real-World Constrained Generation

arXiv:2607. 02628v1 Announce Type: cross Abstract: While diffusion models have revolutionized image synthesis, their application to real-world inverse problems is often hampered by the need for massive datasets and the difficulty of imposing strict physical constraints.

By Kanishk Awadhiya

diffusion benchmarks

arXiv AI

Jun 30

Longitudinal Lesion Inpainting in Brain MRI via 3D Region Aware Diffusion

arXiv:2603. 05693v2 Announce Type: replace-cross Abstract: Accurate longitudinal analysis of brain MRI is often hindered by evolving lesions, which bias automated neuroimaging pipelines.

By Zahra Karimaghaloo, Dumitru Fetco, Haz-Edine Assemlal, Hassan Rivaz, Douglas L. Arnold

diffusion benchmarks safety

arXiv Machine Learning

Jun 4

Plug-and-Play Diffusion Meets ADMM: Dual-Variable Coupling for Robust Medical Image Reconstruction

arXiv:2602. 23214v2 Announce Type: replace-cross Abstract: Plug-and-Play diffusion prior (PnPDP) frameworks have emerged as a powerful paradigm for solving imaging inverse problems by treating pretrained generative models as modular priors.

By Chenhe Du, Xuanyu Tian, Qing Wu, Muyu Liu, Jingyi Yu, Hongjiang Wei, Yuyao Zhang

diffusion fine-tuning benchmarks safety

arXiv AI

Aug 18

Scale-Consistent Posterior Dynamics for Diffusion Inverse Problems

arXiv:2608. 15144v1 Announce Type: cross Abstract: Posterior sampling with a pretrained diffusion prior is governed by a conditional score whose intermediate likelihood component is generally intractable.

By Zhaoqiang Liu, Tongyao Pang, Ruibing Wang, Yang Zheng

diffusion benchmarks

arXiv AI

Jun 8

STREAM: Stochastic Riemannian Flow Matching with Anisotropic Decoder for Digital Histopathology Image Generation

arXiv:2606. 07036v1 Announce Type: cross Abstract: Synthetic histopathology image generation addresses critical challenges in computational pathology, including patient privacy and the growing need for large-scale training data for foundation models.

By Won June Cho, Daeky Jeong, Hyeongyeol Lim, Hongjun Yoon

llms diffusion benchmarks safety

arXiv Machine Learning

Sep 14

Tunable Latent Generative Priors for Compressed Sensing and Inverse Problems

The paper introduces tunable latent priors for diffusion models, normalizing flows, and variational autoencoders using nested dropout. These priors allow the latent dimensionality to adapt to each inverse problem, reducing reconstruction errors compared to fixed-complexity models across tasks such as compressed sensing, inpainting, denoising, and phase retrieval. In linear denoising, the authors derive the optimal latent complexity in closed form, linking it to noise level and signal spectrum.

By Sean Gunn, Jorio Cocola, Oliver De Candido, Vaggos Chatziafratis, Paul Hand

diffusion

Related stories