IRIP-BUAA/A-Survey-on-Remote-Sensing-Foundation-Models-From-Vision-to-Multimodality

A review for remote sensing vision language models

46 commits

updated Jun 24, 2026

See the code

README

A Survey on Remote Sensing Foundation Models: From Vision to Multimodality

This is a repository for "A Survey on Remote Sensing Foundation Models: From Vision to Multimodality".

🌏 Please check out our survey paper: A Survey on Remote Sensing Foundation Models: From Vision to Multimodality

Detail page

You can see details of all papers and datasets here: homepage

Repository Status

This repository maintains the resource list associated with the survey. It is intended to help readers quickly find papers, datasets, models, benchmarks, and agentic remote sensing systems discussed in the survey.

Last curated update: 2026-06-24.

Corrections and additions are welcome. Please see CONTRIBUTING.md before opening a pull request.

Recent Survey Update
Dataset
- Image
- Image+Text
- Video
Model
- Pretrain
- VLM
- MLLM
- Agent
- Other

Recent Survey Update

The 2026 revision broadens the repository beyond early vision and vision-language foundation models. The additions below highlight recent resources on sensor-adaptive pretraining, multimodal reasoning, long-tail datasets, robustness benchmarks, open-vocabulary grounding, and agentic Earth observation.

Recent Models and Methods

Name	Focus	Paper / Project
RAMEN	Resolution-adjustable multimodal encoder for Earth observation	CVPR 2026
THOR	Versatile Earth observation foundation model for climate and society applications	CVPRW 2026
TerraFlow	Multimodal and multitemporal Earth observation representation learning	arXiv 2026
SpectralEarth-FM	Hyperspectral imagery in multimodal Earth observation pretraining	arXiv 2026
FLORO	Multimodal geospatial foundation model across sensors and scales	arXiv 2026
SMARTIES	Spectrum-aware multi-sensor auto-encoder	ICCV 2025
SIGMAE	Spectral-index-guided foundation model for multispectral remote sensing	arXiv 2026
RingMoE	Mixture-of-modality-experts remote sensing foundation model	arXiv 2025
SkySense V2	Unified foundation model for multimodal remote sensing	arXiv 2025
Falcon	Remote sensing vision-language foundation model	arXiv 2025
GeoGround	Unified large vision-language model for remote sensing visual grounding	arXiv 2024
SkyMoE	Vision-language foundation model with mixture of experts	AAAI 2026
Earth-OneVision	MLLM extended to more remote sensing modalities and tasks	arXiv 2026
TerraScope	Pixel-grounded visual reasoning for Earth observation	CVPR 2026
SkyNative	Native multimodal framework for visual evidence reasoning	arXiv 2026
GeoVLM-R1	Reinforcement fine-tuning for remote sensing reasoning	arXiv 2025
RemoteReasoner	Unified geospatial reasoning workflow	arXiv 2025
RemoteZero	Geospatial reasoning with zero human annotations	arXiv 2026
GeoX	Geospatial reasoning through self-play and verifiable rewards	arXiv 2026

Recent Datasets and Benchmarks

Name	Category	Paper / Project
PANGAEA	Global benchmark for geospatial foundation models	arXiv 2024
SpectralEarth-MM	Multimodal, multisensor pretraining data	arXiv 2026
BigEarthNet.txt	Large-scale multi-sensor image-text dataset and benchmark	arXiv 2026
GeoSeg-1M	Open-world geospatial segmentation data	arXiv 2026
UHR-CoZ	Ultra-high-resolution visual focusing / evidence-grounded understanding	arXiv 2026
FusionRS	RGB-infrared remote sensing vision-language dataset	arXiv 2026
Sky-VT-300k	Multimodal in-context segmentation data	CVPR 2026
OpenEarthAgent Dataset	Agentic Earth observation instruction data	arXiv 2026
ChronoEarth-492K	Long-horizon spatiotemporal hyperspectral dataset and benchmark	arXiv 2026
SkyCap	Bitemporal VHR optical-SAR quartets	arXiv 2025
Sentinel2Cap	Human-annotated Sentinel-2 image captioning benchmark	arXiv 2026
VLRS-Bench	Vision-language reasoning benchmark for remote sensing	arXiv 2026
OmniEarth	Geospatial VLM benchmark	arXiv 2026
UHR-Micro	Ultra-high-resolution evidence localization benchmark	arXiv 2026
EarthShift	Robustness benchmark for real-world distribution shifts	arXiv 2026
GeoMMBench	Expert-level multimodal intelligence in geoscience and remote sensing	arXiv 2026
LithoBench	Remote-sensing lithology interpretation benchmark	arXiv 2026
GroundSet	Cadastral-grounded vector-data spatial understanding dataset	arXiv 2026

Recent Agentic and Trustworthy EO Resources

Name	Focus	Paper / Project
RemoteAgent	RL-based agentic MLLMs for Earth observation	arXiv 2026
EO-Gym	Interactive environment for Earth observation agents	arXiv 2026
Earth-Agent	Geospatial agentic system	OpenReview 2026
OpenEarthAgent	Open agent framework for Earth observation	arXiv 2026
ThinkGeo	Remote sensing tool orchestration	arXiv 2025
GeoDisaster	Agentic geospatial reasoning for disaster response	arXiv 2026
IC-EO	Interpretable code-based assistant for Earth observation	arXiv 2026
Bidirectional Semantic Complementary Tool Retrieval	Tool retrieval for remote sensing agents	arXiv 2026
Risk-Aware LLM Agents for Geospatial Data Retrieval	Adversarial evaluation for unsafe tool use	arXiv 2026
Atmospheric Retrieval Hijacking	Prompt-injection risk in remote sensing VLM-RAG	arXiv 2026
No One Knows the State of the Art in Geospatial Foundation Models	Audit of comparability and reproducibility problems	arXiv 2026

Dataset

Image

Dataset Name	Categories	Detailed Info
TAS	Detection	Link
OIRDS	Detection	Link
SZTAKI-INRIA AirChange	Change Detection	Link
UCMerced_LandUse	Classification	Link
ISPRS Potsdam	Segmentation	Link
ISPRS Vaihingen	Segmentation	Link
WHU RS19	Classification	Link
Massachusetts Builds	Segmentation	Link
Massachusetts Roads	Segmentation	Link
SPARCS	Segmentation	Link
RSSCN7	Classification	Link
SAT	Classification	Link
VEDAI	Detection	Link
DLR3k	Detection	Link
HRSC2016	Detection	Link
NWPU-RESISC45	Classification	Link
RS_C11	Classification	Link
SIRI-WHU	Classification	Link
Aerial to Map	Image Generation	Link
AID	Classification	Link
AIST Building Change Detection(ABCD)	Change Detection	Link
CITY-OSM	Segmentation	Link
Dstl Satellite Imagery Feature Detection	Segmentation	Link
OpenSARShip	Detection	Link
RSD46-WHU	Classification	Link
RSI-CB	Classification	Link
SateHaze1k	Image Generation	Link
TGRS-HRRSD	Detection	Link
2018 Open AI Tanzania Building Footprint	Segmentation	Link
Aeroscapes	Segmentation	Link
AIRS	Segmentation	Link
CDD Dataset (season-varying)	Change Detection	Link
DeepGlobe Land Cover Classificat	Segmentation	Link
DeepGlobe Road Detection Challen	Segmentation	Link
DLRSD	Segmentation	Link
DOTA1.0	Detection	Link
EuroSAT	Classification	Link
fMoW	Detection	Link
ITCVD	Detection	Link
LEVIR	Detection	Link
Mapping Challenge	Segmentation	Link
MASATI	Detection	Link
Onera Satellite Change Detection (OSCD)	Change Detection	Link
PatternNet	Classification	Link
RIT-18	Segmentation	Link
Urban Drone Dataset(UDD)	Segmentation	Link
VisDrone2019-DET	Detection	Link
WHDLD	Segmentation	Link
WHU Building Change Detection Dataset	Change Detection	Link
The "Fine" part in WHU_GID	Segmentation	Link
The "Large-scale" part in WHU_GID	Segmentation	Link
The "secenClass" part in WHU_GID	Classification	Link
xView	Detection	Link
38-Cloud	Segmentation	Link
Bijie Landslide Dataset	Segmentation	Link
Bridge Dataset	Detection	Link
Change Detection Dataset(CDD)	Change Detection	Link
DOTA1.5	Detection	Link
DroneDeploy	Segmentation	Link
DSIFN Dataset	Change Detection	Link
GF2 Dataset for 3DFGC	Segmentation	Link
High Resolution Semantic Change (HRSCD)	Change Detection	Link
iSAID	Detection	Link
Multi-temporal Scene WuHan (MtS-WH)	Change Detection	Link
OPTIMAL-31	Classification	Link
ORSSD	Segmentation	Link
RoadTracer	Segmentation	Link
Semantic Drone Dataset	Segmentation	Link
SEN12MS	Segmentation	Link
WHU Building Dataset	Segmentation	Link
95-Cloud	Segmentation	Link
BDCI2020	Segmentation	Link
BH-POOLS	Segmentation	Link
BH-WATERTANKS	Segmentation	Link
Change-Detection-dataset-for-High-resolution-Satellite-Image	Change Detection	Link
Continual Learning Benchmark for Remote	Classification	Link
DroneCrowd	Detection	Link
EORSSD	Segmentation	Link
HRSID	Detection	Link
landcover_ai	Segmentation	Link
LEVIR-CD	Change Detection	Link
MLRSNet	Classification	Link
The "AiRound" part in Multi-View Datasets	Classification	Link
The "CV-BrCT" part in Multi-View Datasets	Classification	Link
RarePlanes	Detection	Link
SEmantic Change detectiON Data(SECOND)	Change Detection	Link
SenseEarth ChangeDetection	Change Detection	Link
Sentinel-2 Cloud Mask Catalogue	Segmentation	Link
Sentinel-2 Multitemporal Cities Pairs	Change Detection	Link
UAVid	Segmentation	Link
WHU Cloud Dataset	Segmentation	Link
WHU Multi-view Dataset	Image Generation	Link
WHU Stereo Dataset	Image Generation	Link
xBD	Change Detection	Link
全国人工智能大赛AI遥感影像	Segmentation	Link
CASIA-aircraft	Detection	Link
CASIA-Ship	Detection	Link
DOTA2.0	Detection	Link
FAIR1M	Detection	Link
LEVIR-CD2	Change Detection	Link
LoveDA	Segmentation	Link
MillionAID	Classification	Link
NaSC-TG2	Classification	Link
S2Looking	Change Detection	Link
SeCo	Single-modal Pre-training	Link
Sun Yat-Sen University (SYSU)-CD	Change Detection	Link
TG1HRSSC	Classification	Link
VISO-Detection	Detection	Link
WHU TCL SatMVS dataset1.0	Image Generation	Link
WHU TCL SatMVS dataset2.0	Image Generation	Link
MiniFrance-DFC22	Segmentation	Link
SAMRS	Segmentation	Link
TOV-RS-balanced	Classification	Link
CACo	Single-modal Pre-training	Link
GEO-Bench	Evaluation	Link
SATIN	Classification	Link
SatlasPretrain	Classification	Link
WHU-Mix (vector) building dataset	Segmentation	Link
Constellation	Detection	Link
Earth Parser Dataset	Segmentation	Link
EarthView	Single-modal Pre-training	Link
GeoPile-2	Multimodal Pre-training	Link
HSODBIT-V1	Detection	Link
SARDet-100K	Detection	Link
SARSim	Detection	-

Image+Text

Dataset Name	Categories	Detailed Info
Sydney-Captions	Image-Text Pair	Link
UCM-Captions	Image-Text Pair	Link
RSICD	Image-Text Pair	Link
RSVQA-HR	VQA	Link
RSVQA-LR	VQA	Link
TextRS	Image-Text Pair	Link
BigEarthNet-MM	Image-Text Pair	Link
FloodNet	VQA	Link
RSIVQA	VQA	Link
RSVQA×BEN	VQA	Link
CDVQA	VQA	Link
GeoVG	Visual Localization	Link
LEVIR-CC	Image-Text Pair	Link
NWPU-Captions	Image-Text Pair	Link
RSITMD	Image-Text Pair	Link
SSL4EO-S12	Multimodal Pre-training	Link
VQA-TextRS	VQA	Link
DIOR_RSVG	Visual Localization	Link
LAION-5B	Image-Text Pair	Link
OPT-RSVG	Visual Localization	Link
RS5M	Image-Text Pair	Link
RSICap	Image-Text Pair	Link
RSIEval	Image-Text Pair	Link
SkyScript	Image-Text Pair	Link
ChatEarthNet	Image-Text Pair	Link
MMEarth	Multimodal Pre-training	Link

Video

Dataset Name	Categories	Detailed Info
UAV123	Object Tracking	Link
VisDrone2019-MOT	Object Tracking	Link
VisDrone2019-SOT	Object Tracking	Link
VisDrone2019-VID	Detection	Link
地空背景下红外图像弱小飞机目标检测跟踪数据集	Object Tracking	Link
VISO-MOT	Object Tracking	Link
VISO-SOT	Object Tracking	Link
复杂背景下红外弱小运动目标检测数据集	Object Tracking	Link
CapERA	Video Caption	Link

Model

Pretrain

Model Name	Paper Name	Published in	Detailed Info
fMoW	Functional Map of the World	CVPR 2018	Link
-	BIGEARTHNET A LARGE-SCALE BENCHMARK ARCHIVE FOR REMOTE SENSINGIMAGE UNDERSTANDING	IGARSS 2019	Link
-	Tile2Vec Unsupervised representation learning for spatially distributed data	AAAI 2019	Link
-	Remote Sensing Image Scene Classification with Self-Supervised Paradigm under Limited Labeled Samples	GRSL 2020	Link
GASSL	Geography-aware self-supervised learning	ICCV 2021	Link
MillionAID	On Creating Benchmark Dataset for Aerial Image Interpretation Reviews, Guidances, and Million-AID	JSTARS 2021	Link
Seco	Seasonal ContrastUnsupervised Pre-Training from Uncurated Remote Sensing Data	CVPR 2021	Link
CMC-RSSR	Self-Supervised Learning of Remote Sensing Scene Representations Using Contrastive Multiview Coding	CVPR 2021	Link
-	Advancing plain vision transformer toward remote sensing foundation model	TGRS 2022	Link
CSPT	Consecutive Pre-Training A Knowledge Transfer Learning Strategy with Relevant Unlabeled Data for Remote Sensing Domain	Remote Sensing 2022	Link
Levir-KR	Geographical Knowledge-Driven RepresentationLearning for Remote Sensing Images	TGRS 2022	Link
-	Global and Local Contrastive Self-Supervised Learning for Semantic Segmentation of HR Remote Sensing Images	TGRS 2022	Link
SatMAE	SatMAE Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagery	NeurIPS 2022	Link
RSBYOL	Self-Supervised Learning for Invariant Representations from Multi-Spectral and SAR Images	JSTARS 2022	Link
MATTER	Self-Supervised Material and Texture Representation Learning for Remote Sensing Tasks	CVPR 2022	Link
DINO-MM	Self-supervised vision transformers for joint sar-optical representation learning	Arxiv 2022	Link
-	Semantic segmentation of remote sensing images with self-supervised semantic-aware inpainting	GRSL 2022	Link
-	A billion-scale foundation model for remote sensing images	Arxiv 2023	Link
-	A Self-Supervised Cross-Modal Remote Sensing Foundation Model with Multi-Domain Representation and Cross-Domain Fusion	IGARSS 2023	Link
-	An Empirical Study of Remote Sensing Pretraining	TGRS 2023	Link
CACo	Change-Aware Sampling and Contrastive Learning for Satellite Images	CVPR 2023	Link
CMID	CMID A Unified Self-Supervised Learning Framework for Remote Sensing Image Understanding	TGRS 2023	Link
CROMA	CROMA Remote Sensing Representations with Contrastive Radar-Optical Masked Autoencoders	NeurIPS 2023	Link
MAE	Cross-Scale MAE A Tale of Multiscale Exploitation in Remote Sensing	NeurIPS 2023	Link
CtxMIM	CtxMIM Context-Enhanced Masked Image Modeling for Remote Sensing Image Understanding	Arxiv 2023	Link
DeCUR	DeCUR decoupling common & unique representations for multimodal self-supervision	Arxiv 2023	Link
DINO-MC	Extending Global-local View Alignment for Self-supervised Learning with Remote Sensing Imagery	Arxiv 2023	Link
EarthPT	EarthPT a foundation model for Earth Observation	NeurIPS CCAI workshop 2023	Link
FG-MAE	Feature Guided Masked Autoencoder for Self-supervised Learning in Remote Sensing	Arxiv 2023	Link
-	FoMo-Bench a multi-modal, multi-scale and multi-task Forest Monitoring Benchmark for remote sensing foundation models	Arxiv 2023	Link
Prithvi	Foundation Models for Generalist Geospatial Artificial Intelligence	Arxiv 2023	Link
Presto	Lightweight, Pre-trained Transformers for Remote Sensing Timeseries	Arxiv 2023	Link
IaI-SimCLR	Multi Modal Multi Objective Contrastive Learning for Sentinel 1-2 Imagery	CVPRW 2023	Link
SAR-JEPA	Predicting Gradient is Better Exploring Self-Supervised Learning for SAR ATR with a Joint-Embedding Predictive Architecture	Arxiv 2023	Link
RingMo-lite	RingMo-lite A Remote Sensing Multi-task Lightweight Network with CNN-Transformer Hybrid Framework	Arxiv 2023	Link
RSPrompter	Rsprompter Learning to prompt for remote sensing instance segmentation based on visual foundation model	Arxiv 2023	Link
SatlasPretrain	SatlasPretrain A Large-Scale Dataset for Remote Sensing Image Understanding	ICCV 2023	Link
-	Scale-MAE A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learning	ICCV 2023	Link
TOV-RS	TOV The original vision model for optical remote sensing image understanding via self-supervised learning	JSTARS 2023	Link
TOV-RS	TOV The Original Vision Model for Optical Remote Sensing Image Understanding via Self-Supervised Learning	JSTARS 2023	Link
GFM	Towards Geospatial Foundation Models via Continual Pretraining	ICCV 2023	Link
USat	USat A Unified Self-Supervised Encoder for Multi-Sensor Satellite Imagery	Arxiv 2023	Link
GeoSense	Generative ConvNet Foundation Model With Sparse Modeling and Low-Frequency Reconstruction for Remote Sensing Image Interpretation	TGRS 2024	Link
GeRSP	Generic Knowledge Boosted Pre-training ForRemote Sensing Images	TGRS 2024	Link
MTP	MTP Advancing Remote Sensing FoundationModel via Multi-Task Pretraining	Arxiv 2024	Link
OFA-Net	One for All Toward Unified Foundation Models for Earth Vision	Arxiv 2024	Link
-	Rethinking Transformers Pre-training for Multi-Spectral Satellite Imagery	CVPR 2024	Link
RingMo	RingMo A Remote Sensing Foundation Model With Masked Image Modeling	TGRS 2024	Link
S2MAE	S2MAE A Spatial-Spectral Pretraining Foundation Model for Spectral Remote Sensing Data	CVPR 2024	Link
U-BARN	Self-Supervised Spatio-Temporal Representation Learning of Satellite Image Time Series	JSTARS 2024	Link
SkySense	SkySense A Multi-Modal Remote Sensing Foundation Model Towards Universal Interpretation for Earth Observation Imagery	CVPR 2024	Link
SpectralGPT	SpectralGPT Spectral Foundation Model	TPAMI 2024	Link
SwiMDiff	SwiMDiff Scene-wide Matching Contrastive Learning with Diffusion Constraint for Remote Sensing Image	Arxiv 2024	Link
-	Multi-source remote sensing pretraining based on contrastive self-supervised learning	Remote Sensing 22	Link
RSICap	RSGPT: A Remote Sensing Vision Language Model and Benchmark	Arxiv 2023	-
HyperSIGMA	HyperSIGMA: Hyperspectral Intelligence Comprehension Foundation Model	IEEE TPAMI 2025	Link
RS-CLIP	RS-CLIP: Zero shot remote sensing scene classification via contrastive vision-language supervision	International Journal of Applied Earth Observation and Geoinformation 2023	Link
StreetCLIP	Learning generalized zero-shot learners for open-domain image geolocalization	Arxiv 2024	-
GeoCLAP	Learning Tri-modal Embeddings for Zero-Shot Soundscape Mapping	Arxiv 2024	-
RSDiff	Rsdiff: Remote sensing image generation from text using diffusion model	Arxiv 2024	-
DiffusionSat	Diffusionsat: A generative foundation model for satellite imagery	Arxiv 2024	-
CRS-Diff	Crs-diff: Controllable generative remote sensing foundation model	Arxiv 2024	-
MetaEarth	Metaearth: A generative foundation model for global-scale remote sensing image generation	Arxiv 2024	-
Skysensegpt	Skysensegpt: A fine-grained instruction tuning dataset and model for remote sensing vision-language understanding	Arxiv 2024	-
RS-Agent	RS-Agent: Automating Remote Sensing Tasks through Intelligent Agents	Arxiv 2024	-
SSLTransformerRS	Self-Supervised Vision Transformers for Land-Cover Segmentation and Classification	Arxiv 2023	-
RingMo-Sense	RingMo-Sense: Remote Sensing Foundation Model for Spatiotemporal Prediction via Spatiotemporal Evolution Disentangling	Arxiv 2023	-
A2-MAE	A2-MAE: A spatial-temporal-spectral unified remote sensing pre-training method based on anchor-aware masked autoencoder	Arxiv 2023	-
MSFE	IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium	IGARSS 2023	-
GeCo	Geographical Supervision Correction for Remote Sensing Representation Learning	Arxiv 2023	-
SoftCon	Multi-label Guided Soft Contrastive Learning for Efficient Earth Observation Pretraining	CVPR 2023	-
Sen12MS	SEN12MS--A curated dataset of georeferenced multi-spectral sentinel-1/2 imagery for deep learning and data fusion	IEEE TGRS 2019	-
BigEarthNet-S2	Bigearthnet: A large-scale benchmark archive for remote sensing image understanding	IEEE TGRS 2019	-
MSAR	Large-scale multi-class SAR image target detection dataset-1.0	Journal of Radars 2022	-
SAR-Ship	SAR target recognition based on cross-domain and cross-task transfer learning	IEEE Access 2019	-
SAMPLE	A SAR dataset for ATR development: the Synthetic and Measured Paired Labeled Experiment (SAMPLE)	SPIE 2019	-
DIOR-RSVG	Rsvg: Exploring data and models for visual grounding on remote sensing data	IEEE TGRS 2023	-
Xview	xview: Objects in context in overhead imagery	Arxiv 2018	-
DIOR-R	Anchor-free oriented proposal generator for object detection	IEEE TGRS 2022	-
SpaceNetv1	Spacenet: A remote sensing dataset and challenge series	Arxiv 2018	-
DynamicEarthNet-S2	Dynamicearthnet: Daily multi-spectral satellite dataset for semantic change segmentation	CVPR 2022	-

VLM

Model Name	Paper Name	Published in	Detailed Info
-	Bootstrapping Interactive Image-Text Alignment for Remote Sensing Image Captioning	Arxiv 2023	Link
-	Language-aware domain generalization network for cross-scene hyperspectral image classification	TGRS 2023	Link
-	Parameter-Efficient Transfer Learning for Remote Sensing Image-Text Retrieval	TGRS 2023	Link
RS5M	RS5M and GeoRSCLIP A Large Scale Vision-Language Dataset and A Large Vision-Language Model for Remote Sensing	Arxiv 2023	Link
S-CLIP	S-CLIP Semi-supervised Vision-Language Learning using Few Specialist Captions	NeurIPS 2023	Link
-	Vlca vision-language aligning model with cross-modal attention for bilingual remote sensing image captioning	J SYST ENG ELECTRON 2023	Link
RS-CapRet	Large Language Models for Captioning and Retrieving Remote Sensing Images	Arxiv 2024	Link
-	Remote Sensing Vision-Language Foundation Models without Annotations via Ground Remote Alignment	ICLR 2024	Link
RemoteCLIP	RemoteCLIP A Vision Language Foundation Model for Remote Sensing	TGRS 2024	Link
SkyScript	SkyScript A Large and Semantically Diverse Vision-Language Dataset for Remote Sensing	AAAI 2024	Link

MLLM

Model Name	Paper Name	Published in	Detailed Info
RSICap	RSGPT A Remote Sensing Vision Language Model and Benchmark	Arxiv 2023	Link
EarthGPT	EarthGPT A Universal Multi-modal Large Language Model for Multi-sensor Image Comprehension in Remote Sensing Domain	Arxiv 2024	Link
Geochat	GeoChat Grounded Large Vision-Language Model for Remote Sensing	CVPR 2024	Link
H2RSVLM	H2RSVLM Towards Helpful and Honest Remote Sensing Large Vision Language Model	Arxiv 2024	Link
LHRS-Instruct	LHRS-Bot Empowering Remote Sensing with VGI-Enhanced Large Multimodal Language Model	Arxiv 2024	Link
Popeye	Popeye A Unified Visual-Language Model for Multi-Source Ship Detection from Remote Sensing Imagery	Arxiv 2024	Link
RS-LLaVA	RS-LLaVA Large Vision Language Model for Joint Captioning and Question Answering in Remote Sensing Imagery	RS 2024	Link
SkyEyeGPT	SkyEyeGPT Unifying Remote Sensing Vision-Language Tasks via Instruction Tuning with Large Language Model	Arxiv 2024	Link

Agent

Model Name	Paper Name	Published in	Detailed Info
Tree-GPT	Tree-GPT Modular Large Language Model Expert System for Forest Remote Sensing Image Understanding and Interactive Analysis	Arxiv 2023	Link
Change-Agent	Change-Agent Towards Interactive Comprehensive Remote Sensing Change Interpretation and Analysis	Arxiv 2024	Link
-	Evaluating Tool-Augmented Agents in Remote Sensing Platforms	ICLR 2024	Link
-	GeoLLM-Engine A Realistic Environment for Building Geospatial Copilots	CVPR 2024	Link
ChatGPT	Remote Sensing ChatGPT Solving Remote Sensing Tasks with ChatGPT and Visual Models	IGARSS 2024	Link

Other

Model Name	Paper Name	Published in	Detailed Info
-	Transforming remote sensing images to textual descriptions	INT J APPL EARTH OBS 2022	Link
-	CSP Self-Supervised Contrastive Spatial Pre-Training for Geospatial-Visual Representations	ICML 2023	Link
GeoCLIP	GeoCLIP Clip-Inspired Alignment between Locations and Images for Effective Worldwide Geo-localization	NeurIPS 2023	Link
-	Good at captioning, bad at counting Benchmarking GPT-4V on Earth observation data	Arxiv 2023	Link
-	On the Promises and Challenges of Multimodal Foundation Models for Geographical, Environmental, Agricultural, and Urban Planning Applications	Arxiv 2023	Link
SatCLIP	SatCLIP Global, General-Purpose Location Embeddings with Satellite Imagery	Arxiv 2023	Link
-	The Potential of Visual ChatGPT for Remote Sensing	RS 2023	Link
-	遥感基础模型发展综述与未来设想	遥感学报 2023	Link
msGFM	Bridging Remote Sensors with Multisensor Geospatial Foundation Models	CVPR 2024	Link
-	Charting New Territories Exploring the Geographic and Geospatial Capabilities of Multimodal LLMs	Arxiv 2024	Link
-	GeoLLM Extracting Geospatial Knowledge from Large Language Models	ICLR 2024	Link
LeMeViT	LeMeViT Efficient Vision Transformer with Learnable Meta Tokens for Remote Sensing Image Interpretation	IJCAI 2024	Link
MMEarth	MMEarth Exploring Multi-Modal Pretext Tasks For Geospatial Representation Learning	Arxiv 2024	Link
DOFA	Neural Plasticity-Inspired Foundation Model for Observing the Earth Crossing Modalities	Arxiv 2024	Link
-	On the Foundations of Earth and Climate Foundation Models	Arxiv 2024	Link
SARATR-X	SARATR-X A Foundation Model for Synthetic Aperture Radar Images Target Recognition	Arxiv 2024	Link
-	Changes to Captions An Attentive Network for Remote Sensing Change Captioning	Arxiv 2023	Link
-	Multi-source interactive stair attention for remote sensing image captioning	RS 2023	Link

Similar repos

ZhanYang-nwpu/Awesome-Remote-Sensing-Multimodal-Large-Language-Model

Multimodal Large Language Models for Remote Sensing (RS-MLLMs): A Survey

410

Jack-bo1220/Awesome-Remote-Sensing-Foundation-Models

1,944

zytx121/Awesome-VLGFM

A Survey on Vision-Language Geo-Foundation Models (VLGFMs)

180

VisionXLab/Awesome-RS-VL-Data

Awesome Remote Sensing Vision-Language Datasets

102

Chen-Yang-Liu/Awesome-RS-SpatioTemporal-VLMs

[IEEE GRSM 2025 🔥] Remote Sensing SpatioTemporal Vision-Language Models: A Comprehensive Survey

226

KyanChen/Awesome-Referring-Remote-Sensing-Image-Segmentation

Awesome Referring Remote Sensing Image Segmentation

sjeeudd/OmniEarth

Dataset

OmniEarth: A Benchmark for Evaluating Vision-Language Models in Geospatial Tasks

henghuiding/Awesome-Multimodal-Referring-Segmentation

[IJCV 2026] Multimodal Referring Segmentation

262

IRIP-BUAA/A-Survey-on-Remote-Sensing-Foundation-Models-From-Vision-to-Multimodality

A review for remote sensing vision language models

46 commits

updated Jun 24, 2026

See the code

README

A Survey on Remote Sensing Foundation Models: From Vision to Multimodality

This is a repository for "A Survey on Remote Sensing Foundation Models: From Vision to Multimodality".

🌏 Please check out our survey paper: A Survey on Remote Sensing Foundation Models: From Vision to Multimodality

Detail page

You can see details of all papers and datasets here: homepage

Repository Status

Last curated update: 2026-06-24.

Corrections and additions are welcome. Please see CONTRIBUTING.md before opening a pull request.

Recent Survey Update
Dataset
- Image
- Image+Text
- Video
Model
- Pretrain
- VLM
- MLLM
- Agent
- Other

Recent Survey Update

Recent Models and Methods

Name	Focus	Paper / Project
RAMEN	Resolution-adjustable multimodal encoder for Earth observation	CVPR 2026
THOR	Versatile Earth observation foundation model for climate and society applications	CVPRW 2026
TerraFlow	Multimodal and multitemporal Earth observation representation learning	arXiv 2026
SpectralEarth-FM	Hyperspectral imagery in multimodal Earth observation pretraining	arXiv 2026
FLORO	Multimodal geospatial foundation model across sensors and scales	arXiv 2026
SMARTIES	Spectrum-aware multi-sensor auto-encoder	ICCV 2025
SIGMAE	Spectral-index-guided foundation model for multispectral remote sensing	arXiv 2026
RingMoE	Mixture-of-modality-experts remote sensing foundation model	arXiv 2025
SkySense V2	Unified foundation model for multimodal remote sensing	arXiv 2025
Falcon	Remote sensing vision-language foundation model	arXiv 2025
GeoGround	Unified large vision-language model for remote sensing visual grounding	arXiv 2024
SkyMoE	Vision-language foundation model with mixture of experts	AAAI 2026
Earth-OneVision	MLLM extended to more remote sensing modalities and tasks	arXiv 2026
TerraScope	Pixel-grounded visual reasoning for Earth observation	CVPR 2026
SkyNative	Native multimodal framework for visual evidence reasoning	arXiv 2026
GeoVLM-R1	Reinforcement fine-tuning for remote sensing reasoning	arXiv 2025
RemoteReasoner	Unified geospatial reasoning workflow	arXiv 2025
RemoteZero	Geospatial reasoning with zero human annotations	arXiv 2026
GeoX	Geospatial reasoning through self-play and verifiable rewards	arXiv 2026

Recent Datasets and Benchmarks

Name	Category	Paper / Project
PANGAEA	Global benchmark for geospatial foundation models	arXiv 2024
SpectralEarth-MM	Multimodal, multisensor pretraining data	arXiv 2026
BigEarthNet.txt	Large-scale multi-sensor image-text dataset and benchmark	arXiv 2026
GeoSeg-1M	Open-world geospatial segmentation data	arXiv 2026
UHR-CoZ	Ultra-high-resolution visual focusing / evidence-grounded understanding	arXiv 2026
FusionRS	RGB-infrared remote sensing vision-language dataset	arXiv 2026
Sky-VT-300k	Multimodal in-context segmentation data	CVPR 2026
OpenEarthAgent Dataset	Agentic Earth observation instruction data	arXiv 2026
ChronoEarth-492K	Long-horizon spatiotemporal hyperspectral dataset and benchmark	arXiv 2026
SkyCap	Bitemporal VHR optical-SAR quartets	arXiv 2025
Sentinel2Cap	Human-annotated Sentinel-2 image captioning benchmark	arXiv 2026
VLRS-Bench	Vision-language reasoning benchmark for remote sensing	arXiv 2026
OmniEarth	Geospatial VLM benchmark	arXiv 2026
UHR-Micro	Ultra-high-resolution evidence localization benchmark	arXiv 2026
EarthShift	Robustness benchmark for real-world distribution shifts	arXiv 2026
GeoMMBench	Expert-level multimodal intelligence in geoscience and remote sensing	arXiv 2026
LithoBench	Remote-sensing lithology interpretation benchmark	arXiv 2026
GroundSet	Cadastral-grounded vector-data spatial understanding dataset	arXiv 2026

Recent Agentic and Trustworthy EO Resources

Name	Focus	Paper / Project
RemoteAgent	RL-based agentic MLLMs for Earth observation	arXiv 2026
EO-Gym	Interactive environment for Earth observation agents	arXiv 2026
Earth-Agent	Geospatial agentic system	OpenReview 2026
OpenEarthAgent	Open agent framework for Earth observation	arXiv 2026
ThinkGeo	Remote sensing tool orchestration	arXiv 2025
GeoDisaster	Agentic geospatial reasoning for disaster response	arXiv 2026
IC-EO	Interpretable code-based assistant for Earth observation	arXiv 2026
Bidirectional Semantic Complementary Tool Retrieval	Tool retrieval for remote sensing agents	arXiv 2026
Risk-Aware LLM Agents for Geospatial Data Retrieval	Adversarial evaluation for unsafe tool use	arXiv 2026
Atmospheric Retrieval Hijacking	Prompt-injection risk in remote sensing VLM-RAG	arXiv 2026
No One Knows the State of the Art in Geospatial Foundation Models	Audit of comparability and reproducibility problems	arXiv 2026

Dataset

Image

Dataset Name	Categories	Detailed Info
TAS	Detection	Link
OIRDS	Detection	Link
SZTAKI-INRIA AirChange	Change Detection	Link
UCMerced_LandUse	Classification	Link
ISPRS Potsdam	Segmentation	Link
ISPRS Vaihingen	Segmentation	Link
WHU RS19	Classification	Link
Massachusetts Builds	Segmentation	Link
Massachusetts Roads	Segmentation	Link
SPARCS	Segmentation	Link
RSSCN7	Classification	Link
SAT	Classification	Link
VEDAI	Detection	Link
DLR3k	Detection	Link
HRSC2016	Detection	Link
NWPU-RESISC45	Classification	Link
RS_C11	Classification	Link
SIRI-WHU	Classification	Link
Aerial to Map	Image Generation	Link
AID	Classification	Link
AIST Building Change Detection(ABCD)	Change Detection	Link
CITY-OSM	Segmentation	Link
Dstl Satellite Imagery Feature Detection	Segmentation	Link
OpenSARShip	Detection	Link
RSD46-WHU	Classification	Link
RSI-CB	Classification	Link
SateHaze1k	Image Generation	Link
TGRS-HRRSD	Detection	Link
2018 Open AI Tanzania Building Footprint	Segmentation	Link
Aeroscapes	Segmentation	Link
AIRS	Segmentation	Link
CDD Dataset (season-varying)	Change Detection	Link
DeepGlobe Land Cover Classificat	Segmentation	Link
DeepGlobe Road Detection Challen	Segmentation	Link
DLRSD	Segmentation	Link
DOTA1.0	Detection	Link
EuroSAT	Classification	Link
fMoW	Detection	Link
ITCVD	Detection	Link
LEVIR	Detection	Link
Mapping Challenge	Segmentation	Link
MASATI	Detection	Link
Onera Satellite Change Detection (OSCD)	Change Detection	Link
PatternNet	Classification	Link
RIT-18	Segmentation	Link
Urban Drone Dataset(UDD)	Segmentation	Link
VisDrone2019-DET	Detection	Link
WHDLD	Segmentation	Link
WHU Building Change Detection Dataset	Change Detection	Link
The "Fine" part in WHU_GID	Segmentation	Link
The "Large-scale" part in WHU_GID	Segmentation	Link
The "secenClass" part in WHU_GID	Classification	Link
xView	Detection	Link
38-Cloud	Segmentation	Link
Bijie Landslide Dataset	Segmentation	Link
Bridge Dataset	Detection	Link
Change Detection Dataset(CDD)	Change Detection	Link
DOTA1.5	Detection	Link
DroneDeploy	Segmentation	Link
DSIFN Dataset	Change Detection	Link
GF2 Dataset for 3DFGC	Segmentation	Link
High Resolution Semantic Change (HRSCD)	Change Detection	Link
iSAID	Detection	Link
Multi-temporal Scene WuHan (MtS-WH)	Change Detection	Link
OPTIMAL-31	Classification	Link
ORSSD	Segmentation	Link
RoadTracer	Segmentation	Link
Semantic Drone Dataset	Segmentation	Link
SEN12MS	Segmentation	Link
WHU Building Dataset	Segmentation	Link
95-Cloud	Segmentation	Link
BDCI2020	Segmentation	Link
BH-POOLS	Segmentation	Link
BH-WATERTANKS	Segmentation	Link
Change-Detection-dataset-for-High-resolution-Satellite-Image	Change Detection	Link
Continual Learning Benchmark for Remote	Classification	Link
DroneCrowd	Detection	Link
EORSSD	Segmentation	Link
HRSID	Detection	Link
landcover_ai	Segmentation	Link
LEVIR-CD	Change Detection	Link
MLRSNet	Classification	Link
The "AiRound" part in Multi-View Datasets	Classification	Link
The "CV-BrCT" part in Multi-View Datasets	Classification	Link
RarePlanes	Detection	Link
SEmantic Change detectiON Data(SECOND)	Change Detection	Link
SenseEarth ChangeDetection	Change Detection	Link
Sentinel-2 Cloud Mask Catalogue	Segmentation	Link
Sentinel-2 Multitemporal Cities Pairs	Change Detection	Link
UAVid	Segmentation	Link
WHU Cloud Dataset	Segmentation	Link
WHU Multi-view Dataset	Image Generation	Link
WHU Stereo Dataset	Image Generation	Link
xBD	Change Detection	Link
全国人工智能大赛AI遥感影像	Segmentation	Link
CASIA-aircraft	Detection	Link
CASIA-Ship	Detection	Link
DOTA2.0	Detection	Link
FAIR1M	Detection	Link
LEVIR-CD2	Change Detection	Link
LoveDA	Segmentation	Link
MillionAID	Classification	Link
NaSC-TG2	Classification	Link
S2Looking	Change Detection	Link
SeCo	Single-modal Pre-training	Link
Sun Yat-Sen University (SYSU)-CD	Change Detection	Link
TG1HRSSC	Classification	Link
VISO-Detection	Detection	Link
WHU TCL SatMVS dataset1.0	Image Generation	Link
WHU TCL SatMVS dataset2.0	Image Generation	Link
MiniFrance-DFC22	Segmentation	Link
SAMRS	Segmentation	Link
TOV-RS-balanced	Classification	Link
CACo	Single-modal Pre-training	Link
GEO-Bench	Evaluation	Link
SATIN	Classification	Link
SatlasPretrain	Classification	Link
WHU-Mix (vector) building dataset	Segmentation	Link
Constellation	Detection	Link
Earth Parser Dataset	Segmentation	Link
EarthView	Single-modal Pre-training	Link
GeoPile-2	Multimodal Pre-training	Link
HSODBIT-V1	Detection	Link
SARDet-100K	Detection	Link
SARSim	Detection	-

Image+Text

Dataset Name	Categories	Detailed Info
Sydney-Captions	Image-Text Pair	Link
UCM-Captions	Image-Text Pair	Link
RSICD	Image-Text Pair	Link
RSVQA-HR	VQA	Link
RSVQA-LR	VQA	Link
TextRS	Image-Text Pair	Link
BigEarthNet-MM	Image-Text Pair	Link
FloodNet	VQA	Link
RSIVQA	VQA	Link
RSVQA×BEN	VQA	Link
CDVQA	VQA	Link
GeoVG	Visual Localization	Link
LEVIR-CC	Image-Text Pair	Link
NWPU-Captions	Image-Text Pair	Link
RSITMD	Image-Text Pair	Link
SSL4EO-S12	Multimodal Pre-training	Link
VQA-TextRS	VQA	Link
DIOR_RSVG	Visual Localization	Link
LAION-5B	Image-Text Pair	Link
OPT-RSVG	Visual Localization	Link
RS5M	Image-Text Pair	Link
RSICap	Image-Text Pair	Link
RSIEval	Image-Text Pair	Link
SkyScript	Image-Text Pair	Link
ChatEarthNet	Image-Text Pair	Link
MMEarth	Multimodal Pre-training	Link

Video

Dataset Name	Categories	Detailed Info
UAV123	Object Tracking	Link
VisDrone2019-MOT	Object Tracking	Link
VisDrone2019-SOT	Object Tracking	Link
VisDrone2019-VID	Detection	Link
地空背景下红外图像弱小飞机目标检测跟踪数据集	Object Tracking	Link
VISO-MOT	Object Tracking	Link
VISO-SOT	Object Tracking	Link
复杂背景下红外弱小运动目标检测数据集	Object Tracking	Link
CapERA	Video Caption	Link

Model

Pretrain

Model Name	Paper Name	Published in	Detailed Info
fMoW	Functional Map of the World	CVPR 2018	Link
-	BIGEARTHNET A LARGE-SCALE BENCHMARK ARCHIVE FOR REMOTE SENSINGIMAGE UNDERSTANDING	IGARSS 2019	Link
-	Tile2Vec Unsupervised representation learning for spatially distributed data	AAAI 2019	Link
-	Remote Sensing Image Scene Classification with Self-Supervised Paradigm under Limited Labeled Samples	GRSL 2020	Link
GASSL	Geography-aware self-supervised learning	ICCV 2021	Link
MillionAID	On Creating Benchmark Dataset for Aerial Image Interpretation Reviews, Guidances, and Million-AID	JSTARS 2021	Link
Seco	Seasonal ContrastUnsupervised Pre-Training from Uncurated Remote Sensing Data	CVPR 2021	Link
CMC-RSSR	Self-Supervised Learning of Remote Sensing Scene Representations Using Contrastive Multiview Coding	CVPR 2021	Link
-	Advancing plain vision transformer toward remote sensing foundation model	TGRS 2022	Link
CSPT	Consecutive Pre-Training A Knowledge Transfer Learning Strategy with Relevant Unlabeled Data for Remote Sensing Domain	Remote Sensing 2022	Link
Levir-KR	Geographical Knowledge-Driven RepresentationLearning for Remote Sensing Images	TGRS 2022	Link
-	Global and Local Contrastive Self-Supervised Learning for Semantic Segmentation of HR Remote Sensing Images	TGRS 2022	Link
SatMAE	SatMAE Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagery	NeurIPS 2022	Link
RSBYOL	Self-Supervised Learning for Invariant Representations from Multi-Spectral and SAR Images	JSTARS 2022	Link
MATTER	Self-Supervised Material and Texture Representation Learning for Remote Sensing Tasks	CVPR 2022	Link
DINO-MM	Self-supervised vision transformers for joint sar-optical representation learning	Arxiv 2022	Link
-	Semantic segmentation of remote sensing images with self-supervised semantic-aware inpainting	GRSL 2022	Link
-	A billion-scale foundation model for remote sensing images	Arxiv 2023	Link
-	A Self-Supervised Cross-Modal Remote Sensing Foundation Model with Multi-Domain Representation and Cross-Domain Fusion	IGARSS 2023	Link
-	An Empirical Study of Remote Sensing Pretraining	TGRS 2023	Link
CACo	Change-Aware Sampling and Contrastive Learning for Satellite Images	CVPR 2023	Link
CMID	CMID A Unified Self-Supervised Learning Framework for Remote Sensing Image Understanding	TGRS 2023	Link
CROMA	CROMA Remote Sensing Representations with Contrastive Radar-Optical Masked Autoencoders	NeurIPS 2023	Link
MAE	Cross-Scale MAE A Tale of Multiscale Exploitation in Remote Sensing	NeurIPS 2023	Link
CtxMIM	CtxMIM Context-Enhanced Masked Image Modeling for Remote Sensing Image Understanding	Arxiv 2023	Link
DeCUR	DeCUR decoupling common & unique representations for multimodal self-supervision	Arxiv 2023	Link
DINO-MC	Extending Global-local View Alignment for Self-supervised Learning with Remote Sensing Imagery	Arxiv 2023	Link
EarthPT	EarthPT a foundation model for Earth Observation	NeurIPS CCAI workshop 2023	Link
FG-MAE	Feature Guided Masked Autoencoder for Self-supervised Learning in Remote Sensing	Arxiv 2023	Link
-	FoMo-Bench a multi-modal, multi-scale and multi-task Forest Monitoring Benchmark for remote sensing foundation models	Arxiv 2023	Link
Prithvi	Foundation Models for Generalist Geospatial Artificial Intelligence	Arxiv 2023	Link
Presto	Lightweight, Pre-trained Transformers for Remote Sensing Timeseries	Arxiv 2023	Link
IaI-SimCLR	Multi Modal Multi Objective Contrastive Learning for Sentinel 1-2 Imagery	CVPRW 2023	Link
SAR-JEPA	Predicting Gradient is Better Exploring Self-Supervised Learning for SAR ATR with a Joint-Embedding Predictive Architecture	Arxiv 2023	Link
RingMo-lite	RingMo-lite A Remote Sensing Multi-task Lightweight Network with CNN-Transformer Hybrid Framework	Arxiv 2023	Link
RSPrompter	Rsprompter Learning to prompt for remote sensing instance segmentation based on visual foundation model	Arxiv 2023	Link
SatlasPretrain	SatlasPretrain A Large-Scale Dataset for Remote Sensing Image Understanding	ICCV 2023	Link
-	Scale-MAE A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learning	ICCV 2023	Link
TOV-RS	TOV The original vision model for optical remote sensing image understanding via self-supervised learning	JSTARS 2023	Link
TOV-RS	TOV The Original Vision Model for Optical Remote Sensing Image Understanding via Self-Supervised Learning	JSTARS 2023	Link
GFM	Towards Geospatial Foundation Models via Continual Pretraining	ICCV 2023	Link
USat	USat A Unified Self-Supervised Encoder for Multi-Sensor Satellite Imagery	Arxiv 2023	Link
GeoSense	Generative ConvNet Foundation Model With Sparse Modeling and Low-Frequency Reconstruction for Remote Sensing Image Interpretation	TGRS 2024	Link
GeRSP	Generic Knowledge Boosted Pre-training ForRemote Sensing Images	TGRS 2024	Link
MTP	MTP Advancing Remote Sensing FoundationModel via Multi-Task Pretraining	Arxiv 2024	Link
OFA-Net	One for All Toward Unified Foundation Models for Earth Vision	Arxiv 2024	Link
-	Rethinking Transformers Pre-training for Multi-Spectral Satellite Imagery	CVPR 2024	Link
RingMo	RingMo A Remote Sensing Foundation Model With Masked Image Modeling	TGRS 2024	Link
S2MAE	S2MAE A Spatial-Spectral Pretraining Foundation Model for Spectral Remote Sensing Data	CVPR 2024	Link
U-BARN	Self-Supervised Spatio-Temporal Representation Learning of Satellite Image Time Series	JSTARS 2024	Link
SkySense	SkySense A Multi-Modal Remote Sensing Foundation Model Towards Universal Interpretation for Earth Observation Imagery	CVPR 2024	Link
SpectralGPT	SpectralGPT Spectral Foundation Model	TPAMI 2024	Link
SwiMDiff	SwiMDiff Scene-wide Matching Contrastive Learning with Diffusion Constraint for Remote Sensing Image	Arxiv 2024	Link
-	Multi-source remote sensing pretraining based on contrastive self-supervised learning	Remote Sensing 22	Link
RSICap	RSGPT: A Remote Sensing Vision Language Model and Benchmark	Arxiv 2023	-
HyperSIGMA	HyperSIGMA: Hyperspectral Intelligence Comprehension Foundation Model	IEEE TPAMI 2025	Link
RS-CLIP	RS-CLIP: Zero shot remote sensing scene classification via contrastive vision-language supervision	International Journal of Applied Earth Observation and Geoinformation 2023	Link
StreetCLIP	Learning generalized zero-shot learners for open-domain image geolocalization	Arxiv 2024	-
GeoCLAP	Learning Tri-modal Embeddings for Zero-Shot Soundscape Mapping	Arxiv 2024	-
RSDiff	Rsdiff: Remote sensing image generation from text using diffusion model	Arxiv 2024	-
DiffusionSat	Diffusionsat: A generative foundation model for satellite imagery	Arxiv 2024	-
CRS-Diff	Crs-diff: Controllable generative remote sensing foundation model	Arxiv 2024	-
MetaEarth	Metaearth: A generative foundation model for global-scale remote sensing image generation	Arxiv 2024	-
Skysensegpt	Skysensegpt: A fine-grained instruction tuning dataset and model for remote sensing vision-language understanding	Arxiv 2024	-
RS-Agent	RS-Agent: Automating Remote Sensing Tasks through Intelligent Agents	Arxiv 2024	-
SSLTransformerRS	Self-Supervised Vision Transformers for Land-Cover Segmentation and Classification	Arxiv 2023	-
RingMo-Sense	RingMo-Sense: Remote Sensing Foundation Model for Spatiotemporal Prediction via Spatiotemporal Evolution Disentangling	Arxiv 2023	-
A2-MAE	A2-MAE: A spatial-temporal-spectral unified remote sensing pre-training method based on anchor-aware masked autoencoder	Arxiv 2023	-
MSFE	IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium	IGARSS 2023	-
GeCo	Geographical Supervision Correction for Remote Sensing Representation Learning	Arxiv 2023	-
SoftCon	Multi-label Guided Soft Contrastive Learning for Efficient Earth Observation Pretraining	CVPR 2023	-
Sen12MS	SEN12MS--A curated dataset of georeferenced multi-spectral sentinel-1/2 imagery for deep learning and data fusion	IEEE TGRS 2019	-
BigEarthNet-S2	Bigearthnet: A large-scale benchmark archive for remote sensing image understanding	IEEE TGRS 2019	-
MSAR	Large-scale multi-class SAR image target detection dataset-1.0	Journal of Radars 2022	-
SAR-Ship	SAR target recognition based on cross-domain and cross-task transfer learning	IEEE Access 2019	-
SAMPLE	A SAR dataset for ATR development: the Synthetic and Measured Paired Labeled Experiment (SAMPLE)	SPIE 2019	-
DIOR-RSVG	Rsvg: Exploring data and models for visual grounding on remote sensing data	IEEE TGRS 2023	-
Xview	xview: Objects in context in overhead imagery	Arxiv 2018	-
DIOR-R	Anchor-free oriented proposal generator for object detection	IEEE TGRS 2022	-
SpaceNetv1	Spacenet: A remote sensing dataset and challenge series	Arxiv 2018	-
DynamicEarthNet-S2	Dynamicearthnet: Daily multi-spectral satellite dataset for semantic change segmentation	CVPR 2022	-

VLM

Model Name	Paper Name	Published in	Detailed Info
-	Bootstrapping Interactive Image-Text Alignment for Remote Sensing Image Captioning	Arxiv 2023	Link
-	Language-aware domain generalization network for cross-scene hyperspectral image classification	TGRS 2023	Link
-	Parameter-Efficient Transfer Learning for Remote Sensing Image-Text Retrieval	TGRS 2023	Link
RS5M	RS5M and GeoRSCLIP A Large Scale Vision-Language Dataset and A Large Vision-Language Model for Remote Sensing	Arxiv 2023	Link
S-CLIP	S-CLIP Semi-supervised Vision-Language Learning using Few Specialist Captions	NeurIPS 2023	Link
-	Vlca vision-language aligning model with cross-modal attention for bilingual remote sensing image captioning	J SYST ENG ELECTRON 2023	Link
RS-CapRet	Large Language Models for Captioning and Retrieving Remote Sensing Images	Arxiv 2024	Link
-	Remote Sensing Vision-Language Foundation Models without Annotations via Ground Remote Alignment	ICLR 2024	Link
RemoteCLIP	RemoteCLIP A Vision Language Foundation Model for Remote Sensing	TGRS 2024	Link
SkyScript	SkyScript A Large and Semantically Diverse Vision-Language Dataset for Remote Sensing	AAAI 2024	Link

MLLM

Model Name	Paper Name	Published in	Detailed Info
RSICap	RSGPT A Remote Sensing Vision Language Model and Benchmark	Arxiv 2023	Link
EarthGPT	EarthGPT A Universal Multi-modal Large Language Model for Multi-sensor Image Comprehension in Remote Sensing Domain	Arxiv 2024	Link
Geochat	GeoChat Grounded Large Vision-Language Model for Remote Sensing	CVPR 2024	Link
H2RSVLM	H2RSVLM Towards Helpful and Honest Remote Sensing Large Vision Language Model	Arxiv 2024	Link
LHRS-Instruct	LHRS-Bot Empowering Remote Sensing with VGI-Enhanced Large Multimodal Language Model	Arxiv 2024	Link
Popeye	Popeye A Unified Visual-Language Model for Multi-Source Ship Detection from Remote Sensing Imagery	Arxiv 2024	Link
RS-LLaVA	RS-LLaVA Large Vision Language Model for Joint Captioning and Question Answering in Remote Sensing Imagery	RS 2024	Link
SkyEyeGPT	SkyEyeGPT Unifying Remote Sensing Vision-Language Tasks via Instruction Tuning with Large Language Model	Arxiv 2024	Link

Agent

Model Name	Paper Name	Published in	Detailed Info
Tree-GPT	Tree-GPT Modular Large Language Model Expert System for Forest Remote Sensing Image Understanding and Interactive Analysis	Arxiv 2023	Link
Change-Agent	Change-Agent Towards Interactive Comprehensive Remote Sensing Change Interpretation and Analysis	Arxiv 2024	Link
-	Evaluating Tool-Augmented Agents in Remote Sensing Platforms	ICLR 2024	Link
-	GeoLLM-Engine A Realistic Environment for Building Geospatial Copilots	CVPR 2024	Link
ChatGPT	Remote Sensing ChatGPT Solving Remote Sensing Tasks with ChatGPT and Visual Models	IGARSS 2024	Link

Other

Model Name	Paper Name	Published in	Detailed Info
-	Transforming remote sensing images to textual descriptions	INT J APPL EARTH OBS 2022	Link
-	CSP Self-Supervised Contrastive Spatial Pre-Training for Geospatial-Visual Representations	ICML 2023	Link
GeoCLIP	GeoCLIP Clip-Inspired Alignment between Locations and Images for Effective Worldwide Geo-localization	NeurIPS 2023	Link
-	Good at captioning, bad at counting Benchmarking GPT-4V on Earth observation data	Arxiv 2023	Link
-	On the Promises and Challenges of Multimodal Foundation Models for Geographical, Environmental, Agricultural, and Urban Planning Applications	Arxiv 2023	Link
SatCLIP	SatCLIP Global, General-Purpose Location Embeddings with Satellite Imagery	Arxiv 2023	Link
-	The Potential of Visual ChatGPT for Remote Sensing	RS 2023	Link
-	遥感基础模型发展综述与未来设想	遥感学报 2023	Link
msGFM	Bridging Remote Sensors with Multisensor Geospatial Foundation Models	CVPR 2024	Link
-	Charting New Territories Exploring the Geographic and Geospatial Capabilities of Multimodal LLMs	Arxiv 2024	Link
-	GeoLLM Extracting Geospatial Knowledge from Large Language Models	ICLR 2024	Link
LeMeViT	LeMeViT Efficient Vision Transformer with Learnable Meta Tokens for Remote Sensing Image Interpretation	IJCAI 2024	Link
MMEarth	MMEarth Exploring Multi-Modal Pretext Tasks For Geospatial Representation Learning	Arxiv 2024	Link
DOFA	Neural Plasticity-Inspired Foundation Model for Observing the Earth Crossing Modalities	Arxiv 2024	Link
-	On the Foundations of Earth and Climate Foundation Models	Arxiv 2024	Link
SARATR-X	SARATR-X A Foundation Model for Synthetic Aperture Radar Images Target Recognition	Arxiv 2024	Link
-	Changes to Captions An Attentive Network for Remote Sensing Change Captioning	Arxiv 2023	Link
-	Multi-source interactive stair attention for remote sensing image captioning	RS 2023	Link

Similar repos

ZhanYang-nwpu/Awesome-Remote-Sensing-Multimodal-Large-Language-Model

Multimodal Large Language Models for Remote Sensing (RS-MLLMs): A Survey

410

Jack-bo1220/Awesome-Remote-Sensing-Foundation-Models

1,944

zytx121/Awesome-VLGFM

A Survey on Vision-Language Geo-Foundation Models (VLGFMs)

180

VisionXLab/Awesome-RS-VL-Data

Awesome Remote Sensing Vision-Language Datasets

102

Chen-Yang-Liu/Awesome-RS-SpatioTemporal-VLMs

[IEEE GRSM 2025 🔥] Remote Sensing SpatioTemporal Vision-Language Models: A Comprehensive Survey

226

KyanChen/Awesome-Referring-Remote-Sensing-Image-Segmentation

Awesome Referring Remote Sensing Image Segmentation

sjeeudd/OmniEarth

Dataset

OmniEarth: A Benchmark for Evaluating Vision-Language Models in Geospatial Tasks

henghuiding/Awesome-Multimodal-Referring-Segmentation

[IJCV 2026] Multimodal Referring Segmentation

262

IRIP-BUAA/A-Survey-on-Remote-Sensing-Foundation-Models-From-Vision-to-Multimodality

README

A Survey on Remote Sensing Foundation Models: From Vision to Multimodality

Detail page

Repository Status

Table of Contents

Recent Survey Update

Recent Models and Methods

Recent Datasets and Benchmarks

Recent Agentic and Trustworthy EO Resources

Dataset

Image

Image+Text

Video

Model

Pretrain

VLM

MLLM

Agent

Other

Similar repos

IRIP-BUAA/A-Survey-on-Remote-Sensing-Foundation-Models-From-Vision-to-Multimodality

README

A Survey on Remote Sensing Foundation Models: From Vision to Multimodality

Detail page

Repository Status

Table of Contents

Recent Survey Update

Recent Models and Methods

Recent Datasets and Benchmarks

Recent Agentic and Trustworthy EO Resources

Dataset

Image

Image+Text

Video

Model

Pretrain

VLM

MLLM

Agent

Other

Similar repos