Any-Optical-Model: A Universal Foundation Model for Optical Remote Sensing

TL;DR

This paper introduces Any Optical Model (AOM), a universal foundation model for optical remote sensing that effectively handles arbitrary band configurations, sensor types, and resolutions, improving robustness and generalization.

Contribution

AOM is the first universal remote sensing foundation model that explicitly encodes spectral identity and adapts to various resolutions, addressing limitations of fixed-band pretrained models.

Findings

Achieves state-of-the-art performance on multiple datasets.

Robust to missing bands, sensor differences, and resolution changes.

Outperforms existing models in challenging real-world scenarios.

Abstract

Optical satellites, with their diverse band layouts and ground sampling distances, supply indispensable evidence for tasks ranging from ecosystem surveillance to emergency response. However, significant discrepancies in band composition and spatial resolution across different optical sensors present major challenges for existing Remote Sensing Foundation Models (RSFMs). These models are typically pretrained on fixed band configurations and resolutions, making them vulnerable to real world scenarios involving missing bands, cross sensor fusion, and unseen spatial scales, thereby limiting their generalization and practical deployment. To address these limitations, we propose Any Optical Model (AOM), a universal RSFM explicitly designed to accommodate arbitrary band compositions, sensor types, and resolution scales. To preserve distinctive spectral characteristics even when bands are missing or newly introduced, AOM introduces a spectrum-independent tokenizer that assigns each channel a dedicated band embedding, enabling explicit encoding of spectral identity. To effectively capture texture and contextual patterns from sub-meter to hundred-meter imagery, we design a multi-scale adaptive patch embedding mechanism that dynamically modulates the receptive field. Furthermore, to maintain global semantic consistency across varying resolutions, AOM incorporates a multi-scale semantic alignment mechanism alongside a channel-wise self-supervised masking and reconstruction pretraining strategy that jointly models spectral-spatial relationships. Extensive experiments on over 10 public datasets, including those from Sentinel-2, Landsat, and HLS, demonstrate that AOM consistently achieves state-of-the-art (SOTA) performance under challenging conditions such as band missing, cross sensor, and cross resolution settings.