AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

SkySense V2: A Unified Foundation Model for Multi-modal Remote Sensing

Yingying Zhang, Lixiang Ru, Kang Wu, Lei Yu, Lei Liang, Yansheng Li, Jingdong Chen

ICCV 2025 · Vision-language and multimodal › Cross-modal learning · approach: Multi-modality image fusion · 31 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace SkySense separate per-modality backbones with a unified backbone (SkySense V2)SkySense V2 · Model sizeparameters: 1.26 billion -> 665 millionImproved
replace SkySense with SkySense V2SkySense V2 · OSCDF1: 60.06 -> 65.29Improved
replace SkySense with SkySense V2SkySense V2 · Change detection (3 datasets)average score: 2.7% average gainImproved
replace SkySense with SkySense V2SkySense V2 · Semantic segmentation (4 datasets)average score: 1.5% higher on averageImproved
replace SkySense with SkySense V2SkySense V2 · Object detection (DIOR, DIOR-R, FAIR1M)mAP: 1.1% average mAP gainImproved
replace SkySense with SkySense V2SkySense V2 · PASTIS-MMoverall accuracy: 1.0% average gainImproved
replace SkySense with SkySense V2 at low training ratioSkySense V2 · RESISC-45 (TR=20%)OA: 96.32 -> 97.24 (SatMAE++ 97.48)Mixed
add temporal Sentinel-2 series (S2-Ts) instead of single S2 imageSkySense V2 · PASTIS-MMoverall accuracy: 75.0 -> 85.5Improved
add S2 and S1 modalities to single S1 inputSkySense V2 · BEN-MMaccuracy: 86.5 -> 93.8Improved
add Planet. + S2 + S1 to Planet. onlySkySense V2 · Dyna.-MMmIoU: 47.6 -> 48.9Improved
add modality-specific prompt tokens (ablation)SkySense V2 · AID / RESISC-45 (k-NN)k-NN accuracyImproved
add Mixture of Experts scaling (ablation)SkySense V2 · AID / RESISC-45 (k-NN)k-NN accuracyImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy