AnyBand-Diff: A Unified Remote Sensing Image Generation and Band Repair Framework with Spectral Priors

TL;DR

AnyBand-Diff is a spectral-prior-guided diffusion framework designed for robust spectral reconstruction in remote sensing, ensuring physical plausibility and radiometric consistency in generated images.

Contribution

It introduces a novel diffusion model with spectral priors, physics-guided sampling, and multi-scale physical loss for physically consistent remote sensing image generation.

Findings

Effective spectral reconstruction from arbitrary band subsets.

Enhanced radiometric fidelity in generated images.

Improved physical plausibility in Earth observation data.

Abstract

Existing diffusion models have made significant progress in generating realistic images. However, their direct adaptation to remote sensing imagery often disregards intrinsic physical laws. This oversight frequently leads to spectral distortion and radiometric inconsistency, severely limiting the scientific utility of generated data. To address this issue, this paper introduces AnyBand-Diff, a novel spectral-prior-guided diffusion framework tailored for robust spectral reconstruction. Specifically, we design a Masked Conditional Diffusion backbone integrated with a dual stochastic masking strategy, empowering the model to recover complete spectral information from arbitrary band subsets. Subsequently, to ensure radiometric fidelity, a Physics-Guided Sampling mechanism is proposed, leveraging gradients from a differentiable physical model to explicitly steer the denoising trajectory toward the manifold of physically plausible solutions. Furthermore, a Multi-Scale Physical Loss is formulated to enforce rigorous constraints across pixel, region, and global levels in a joint manner. Extensive experiments confirm the effectiveness of AnyBand-Diff in generating reliable imagery and achieving accurate spectral reconstruction, contributing to the advancement of physics-aware generative methods for Earth observation.