Research map / Image generation / Image restoration
Any-Optical-Model: A Universal Foundation Model for Optical Remote Sensing
Xuyang Li, Chenyu Li, Danfeng Hong
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add InfoNCE multi-scale semantic alignment to MSE reconstruction pretraining (ablation) | AOM · EuroSAT linear probing | accuracy (%): 96.45 -> 97.87 | Improved |
| add InfoNCE multi-scale semantic alignment to MSE reconstruction pretraining (ablation) | AOM · UCM | accuracy (%): 91.28 -> 93.57 | Improved |
| add InfoNCE multi-scale semantic alignment to MSE reconstruction pretraining (ablation) | AOM · SPARCS | mIoU (%): 66.7 -> 68.5 | Improved |
| use channel index encoding instead of wavelength embedding (ablation) | AOM · EuroSAT, UCM, SPARCS | accuracy / mIoU: EuroSAT 97.72 -> 97.87; UCM 92.81 -> 93.57; SPARCS 67.7 -> 68.5 | No clear effect |
| per-band tokenizer with channel index encoding (SiTok) for band-flexible input | AOM · EuroSAT linear probing, 3 bands | accuracy (%): 95.50% with only 3 bands; 2.28-19.09% higher than competitors | Improved |
| vary patch size from coarse to fine with multi-scale adaptive patch embedding (ablation) | AOM · UCM and SPARCS | accuracy / mIoU | No clear effect |
| AOM versus second-best RSFM on cashew-plantation | AOM · Geo-Bench m-cashew-plantation | mIoU: 53.8 -> 68.3 | Improved |
| AOM versus CROMA on m-SA-crop-type | AOM · Geo-Bench m-SA-crop-type | mIoU: 31.4 -> 31.0 | Hurt |
Closest papers by meaning
- Alliance: All-in-One Spectral-Spatial-Frequency Awareness Foundation Model (TPAMI 2025 · similarity 0.88)
- AnySat: One Earth Observation Model for Many Resolutions, Scales, and Modalities (CVPR 2025 · similarity 0.86)
- S2MAE: A Spatial-Spectral Pretraining Foundation Model for Spectral Remote Sensing Data (CVPR 2024 · similarity 0.86)
- SkySense: A Multi-Modal Remote Sensing Foundation Model Towards Universal Interpretation for Earth Observation Imagery (CVPR 2024 · similarity 0.86)
- Bridging Remote Sensors with Multisensor Geospatial Foundation Models (CVPR 2024 · similarity 0.85)
- Building Bridges across Spatial and Temporal Resolutions: Reference-Based Super-Resolution via Change Priors and Conditional Diffusion Model (CVPR 2024 · similarity 0.85)
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.
