← Back to all news
arXiv Machine Learning By Shuo Li, Mike Davies, Mehrdad Yaghoobi

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

Read the original on arXiv Machine Learning →

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.

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.

Related stories

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
diffusionbenchmarks
More like this →
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-visionbenchmarks
More like this →