0

RemoteVAR: Autoregressive Visual Modeling for Remote Sensing Change Detection

RemoteVAR is a visual autoregressive framework for remote sensing change detection that improves upon existing methods through multi-resolution feature fusion and autoregressive training tailored for change map prediction.

Year
2026
Venue
arXiv 2026
Authors
2
Hosting
Abstract onlyARXIV-DEFAULT

Cite

Notes

Only stored in your browser.

Attribution

Abstract & full text
arxiv.org/abs/2601.11898ARXIV-DEFAULT
TL;DR
Semantic Scholar
Attribution policy →

Abstract

Remote sensing change detection aims to localize and characterize scene changes between two time points and is central to applications such as environmental monitoring and disaster assessment. Meanwhile, visual autoregressive models (VARs) have recently shown impressive image generation capability, but their adoption for pixel-level discriminative tasks remains limited due to weak controllability, suboptimal dense prediction performance and exposure bias. We introduce RemoteVAR, a new VAR-based change detection framework that addresses these limitations by conditioning autoregressive prediction on multi-resolution fused bi-temporal features via cross-attention, and by employing an autoregressive training strategy designed specifically for change map prediction. Extensive experiments on standard change detection benchmarks show that RemoteVAR delivers consistent and significant improvements over strong diffusion-based and transformer-based baselines, establishing a competitive autoregressive alternative for remote sensing change detection. Code will be available https://github.com/yilmazkorkmaz1/RemoteVAR{here}.

Authors

2