UniverSat: Resolution- and Modality-Agnostic Transformers for Earth Observation
Summary
UniverSat introduces a Universal Patch Encoder for Vision Transformers that enables robust, sensor-agnostic spatial feature extraction across diverse Earth Observation data types, achieving strong results on classification and segmentation benchmarks.
View Cached Full Text
Cached at: 06/23/26, 05:40 AM
Paper page - UniverSat: Resolution- and Modality-Agnostic Transformers for Earth Observation
Source: https://huggingface.co/papers/2606.23503
Abstract
UniverSat introduces a Universal Patch Encoder for Vision Transformers that enables robust, sensor-agnostic spatial feature extraction across diverse Earth Observation data types.
Vision Transformers(ViT) dominate computer vision. However, their reliance on rigidpatch projectorshinders transfer toEarth Observation(EO), where input modalities, scales, and resolutions vary widely. We introduce UniverSat, a ViT-style backbone built around aUniversal Patch Encoderthat maps patches from arbitrary spatial, spectral, and temporal resolutions, and from both optical and non-optical sensors, into a shared embedding space with a shared set of weights. This enables training a single model on heterogeneousmultimodal corporaviaself-supervision, yielding robust, sensor-agnosticspatial features. We validate this approach with strong results acrossclassificationandsegmentationon standard EO benchmarks from GeoBench, PANGEABench, and SpectralEarth. Our code and models are available at https://github.com/gastruc/UniverSat.
View arXiv pageView PDFProject pageGitHub1Add to collection
Models citing this paper1
#### g-astruc/UniverSat Image Feature Extraction• 0.2B• Updatedabout 1 hour ago • 5 • 3
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2606.23503 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2606.23503 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
ViT-Up: Faithful Feature Upsampling for Vision Transformers
ViT-Up introduces a task-agnostic feature upsampler for Vision Transformers that predicts features at arbitrary continuous image coordinates, enabling dense feature maps at any resolution and improving dense prediction and semantic correspondence benchmarks. It outperforms prior state-of-the-art upsamplers, with gains of up to +2.07 mIoU on Cityscapes and +4.17 [email protected] on SPair-71k.
UniT: Unified Geometry Learning with Group Autoregressive Transformer
UniT is a unified feed-forward model for geometry perception using a Group Autoregressive Transformer that integrates multiple paradigms (online/offline, multi-modal, long-horizon) while maintaining metric-scale accuracy via scale-adaptive loss and queue-style KV caching. It achieves state-of-the-art performance on ten benchmarks spanning seven tasks.
HADT: A Heterogeneous Multi-Agent Differential Transformer for Autonomous Earth Observation Satellite Cluster
This paper proposes HADT, a transformer-based architecture for autonomous resource management in heterogeneous satellite clusters for Earth observation, using differential attention and relational tokenization. Experiments show significant improvements over baselines and strong adaptability to varying cluster sizes.
Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation
Tuna-2 is a unified multimodal model that achieves state-of-the-art performance by processing visual understanding and generation directly from pixel embeddings, eliminating the need for pretrained vision encoders.
SEAOTTER: Sensor Embedded Autoencoding with One-Time Transcode for Efficient Reconstruction
Introduces SEAOTTER, a compression framework for cloud robotics that combines learned latent representations with standard JPEG compatibility, achieving faster encoding/decoding and higher accuracy at extreme compression ratios.