AI Paper Atlas

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

Any2Any: Unified Arbitrary Modality Translation for Remote Sensing

Haoyang Chen, Jing Zhang, Di Wang, Hebaixu Wang, Shiqin Wang, Pohsun Huang, Jiayuan Li, Haonan Guo, Zheng Wang, Bo Du

ICML 2026 · Vision-language and multimodal › Cross-modal learning · approach: Multi-modality image fusion · 0 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
add target-specific residual adapter (ablation)Any2Any (SAR->RGB only) · RST-1M test, SAR->RGBPSNR: 20.68 -> 20.88Improved
add target-specific residual adapter (ablation)Any2Any (SAR->RGB only) · RST-1M test, SAR->RGBRMSE: 28.51 -> 27.89Improved
continue from pretrained model instead of training from scratch when adding RGB->SAR (ablation)Any2Any · RST-1M test, SAR->RGBPSNR: 19.63 -> 21.44Improved
continue from pretrained model instead of training from scratch when adding RGB->SAR (ablation)Any2Any · RST-1M test, SAR->RGBRMSE: 32.83 -> 25.87Improved
add all SAR->other translation directions to training (ablation)Any2Any · RST-1M test, SAR->RGBPSNR: 20.88 -> 22.06Improved
add all other->RGB translation directions to training (ablation)Any2Any · RST-1M test, SAR->RGBPSNR: 20.88 -> 21.36Improved
train on all 14 directions (Any->Any) (ablation)Any2Any · RST-1M test, SAR->RGBPSNR: 20.88 -> 22.25Improved
one unified model instead of pairwise models (ablation)Any2Any-S · RST-1M test, SAR->RGBPSNR: 20.81 -> 22.25Improved
one unified model instead of pairwise models (ablation)Any2Any-S · RST-1M test, RGB->PANPSNR: 32.46 -> 31.30Improved
unified model instead of pairwise models (ablation)Any2Any-S · RST-1M test, NIR->RGBPSNR: 23.01 -> 23.01No clear effect
scale DiT backbone from S to LAny2Any · RST-1M test, SAR->RGBPSNR: 22.25 -> 25.20Improved
use unified Any2Any-L instead of best pairwise baselineAny2Any-L · RST-1M test, 14 translation tasksPSNRImproved

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