Earth-OneVision is a unified 2B-parameter RS-MLLM supporting six modalities and nine tasks via FGVLA, SLIS, and PCMA mechanisms plus a 34M QA-pair dataset, reporting competitive or superior benchmark results versus larger models.
hub
xView: Objects in Context in Overhead Imagery
17 Pith papers cite this work, alongside 87 external citations. Polarity classification is still indexing.
17
Pith papers citing it
87
external citations · Pith
abstract
We introduce a new large-scale dataset for the advancement of object detection techniques and overhead object detection research. This satellite imagery dataset enables research progress pertaining to four key computer vision frontiers. We utilize a novel process for geospatial category detection and bounding box annotation with three stages of quality control. Our data is collected from WorldView-3 satellites at 0.3m ground sample distance, providing higher resolution imagery than most public satellite imagery datasets. We compare xView to other object detection datasets in both natural and overhead imagery domains and then provide a baseline analysis using the Single Shot MultiBox Detector. xView is one of the largest and most diverse publicly available object-detection datasets to date, with over 1 million objects across 60 classes in over 1,400 km^2 of imagery.
hub tools
citation-role summary
dataset 3
background 1
citation-polarity summary
representative citing papers
Count Anything is a generalist model for text-guided object counting that uses Region-level Sparse and Pixel-level Dense counters on the CLOC cross-domain dataset of 220K images.
HCBM apply Hoeffding functional decomposition to concept scores for non-linear sparse predictions in CBMs, with claimed robustness to leakage and strong results on overhead image tasks.
DiffVAS combines diffusion-based reconstruction of unobserved geospatial regions with target-conditioned RL planning to enable multi-object visual active search in partially observable environments.
The paper delivers the first comprehensive review and unified taxonomy of agentic AI in remote sensing, covering single-agent copilots, multi-agent systems, planning mechanisms, benchmarks, and a roadmap while noting limitations in grounding and safety.
MMLandmarks supplies 197k aerial and 329k ground images plus text and GPS for 18,557 landmarks to benchmark multimodal geo-spatial understanding.
VLMs show a resolution illusion on UHR Earth observation imagery where higher resolution does not improve micro-target perception; UHR-Micro benchmark and MAP-Agent address this via evidence-centered active inspection.
EO-Gym supplies an executable multimodal environment and 9k-trajectory benchmark that turns Earth Observation into a tool-using, multi-step reasoning task, revealing that current VLMs struggle on temporal and cross-sensor workflows while fine-tuning lifts Pass@3 from 0.49 to 0.74.
Noise2Map repurposes diffusion model denoising into a direct predictor for semantic segmentation and change detection tasks in remote sensing, achieving top average ranks on benchmark datasets.
ASAHI adaptively slices high-res images into 6 or 12 patches, adds slicing-assisted fine-tuning, and uses Cluster-DIoU-NMS to hit 56.8% mAP on VisDrone2019 and 22.7% on xView while running 20-25% faster than fixed slicing baselines.
TinySet-9M dataset and DEAL point-prompted framework deliver 31.4% relative AP75 gain over supervised baselines for small object detection with one click at inference and generalization to unseen categories.
A million-box 159-class remote-sensing dataset plus a GSD- and hierarchy-aware detector yields ~5 mAP average gains over fully supervised baselines on nine external benchmarks with no target training.
The study systematically evaluates composed image retrieval methods on remote sensing imagery, introduces the xView2-CIR dataset for change-centric disaster retrieval, and finds training-free methods provide strong baselines.
HMR-Net introduces hierarchical routing with global dataset-level and local scene-level modularity plus conditional experts to improve cross-domain aerial object detection and enable novel category recognition without retraining.
Object detection on satellite images enables estimation of average annual daily truck traffic as a proof-of-concept for regions lacking ground monitoring.
A multi-cue pipeline combining deep learning appearance detection and flux tensor spatio-temporal filtering achieves high-precision moving vehicle detection in aerial videos while enabling over 100:1 semantic compression.
Nearest-neighbor interpolation matches multi-scale deep super-resolution performance for vehicle detection on 4x-upscaled xView satellite imagery, with a 0.0002 AP difference.
citing papers explorer
-
Earth-OneVision: Extending Remote Sensing Multimodal Large Language Models to More Sensor Modalities and Tasks
Earth-OneVision is a unified 2B-parameter RS-MLLM supporting six modalities and nine tasks via FGVLA, SLIS, and PCMA mechanisms plus a 34M QA-pair dataset, reporting competitive or superior benchmark results versus larger models.
-
Count Anything
Count Anything is a generalist model for text-guided object counting that uses Region-level Sparse and Pixel-level Dense counters on the CLOC cross-domain dataset of 220K images.
-
Hoeffding Concept Bottleneck Models with Applications to Overhead Images
HCBM apply Hoeffding functional decomposition to concept scores for non-linear sparse predictions in CBMs, with claimed robustness to leakage and strong results on overhead image tasks.
-
DiffVAS: Diffusion-Guided Visual Active Search in Partially Observable Environments
DiffVAS combines diffusion-based reconstruction of unobserved geospatial regions with target-conditioned RL planning to enable multi-object visual active search in partially observable environments.
-
Agentic AI in Remote Sensing: Foundations, Taxonomy, and Emerging Systems
The paper delivers the first comprehensive review and unified taxonomy of agentic AI in remote sensing, covering single-agent copilots, multi-agent systems, planning mechanisms, benchmarks, and a roadmap while noting limitations in grounding and safety.
-
MMLANDMARKS: a Cross-View Instance-Level Benchmark for Geo-Spatial Understanding
MMLandmarks supplies 197k aerial and 329k ground images plus text and GPS for 18,557 landmarks to benchmark multimodal geo-spatial understanding.
-
UHR-Micro: Diagnosing and Mitigating the Resolution Illusion in Earth Observation VLMs
VLMs show a resolution illusion on UHR Earth observation imagery where higher resolution does not improve micro-target perception; UHR-Micro benchmark and MAP-Agent address this via evidence-centered active inspection.
-
EO-Gym: A Multimodal, Interactive Environment for Earth Observation Agents
EO-Gym supplies an executable multimodal environment and 9k-trajectory benchmark that turns Earth Observation into a tool-using, multi-step reasoning task, revealing that current VLMs struggle on temporal and cross-sensor workflows while fine-tuning lifts Pass@3 from 0.49 to 0.74.
-
Noise2Map: End-to-End Diffusion Model for Semantic Segmentation and Change Detection
Noise2Map repurposes diffusion model denoising into a direct predictor for semantic segmentation and change detection tasks in remote sensing, achieving top average ranks on benchmark datasets.
-
Adaptive Slicing-Assisted Hyper Inference for Enhanced Small Object Detection in High-Resolution Imagery
ASAHI adaptively slices high-res images into 6 or 12 patches, adds slicing-assisted fine-tuning, and uses Cluster-DIoU-NMS to hit 56.8% mAP on VisDrone2019 and 22.7% on xView while running 20-25% faster than fixed slicing baselines.
-
Generalized Small Object Detection:A Point-Prompted Paradigm and Benchmark
TinySet-9M dataset and DEAL point-prompted framework deliver 31.4% relative AP75 gain over supervised baselines for small object detection with one click at inference and generalization to unseen categories.
-
LEVIRDet: A Million-Scale 159-Category Dataset and Foundation Model for Universal Remote Sensing Object Detection
A million-box 159-class remote-sensing dataset plus a GSD- and hierarchy-aware detector yields ~5 mAP average gains over fully supervised baselines on nine external benchmarks with no target training.
-
Benchmarking Composed Image Retrieval for Applied Earth Observation
The study systematically evaluates composed image retrieval methods on remote sensing imagery, introduces the xView2-CIR dataset for change-centric disaster retrieval, and finds training-free methods provide strong baselines.
-
HMR-Net: Hierarchical Modular Routing for Cross-Domain Object Detection in Aerial Images
HMR-Net introduces hierarchical routing with global dataset-level and local scene-level modularity plus conditional experts to improve cross-domain aerial object detection and enable novel category recognition without retraining.
-
Truck Traffic Monitoring with Satellite Images
Object detection on satellite images enables estimation of average annual daily truck traffic as a proof-of-concept for regions lacking ground monitoring.
-
Multi-Cue Vehicle Detection for Semantic Video Compression In Georegistered Aerial Videos
A multi-cue pipeline combining deep learning appearance detection and flux tensor spatio-temporal filtering achieves high-precision moving vehicle detection in aerial videos while enabling over 100:1 semantic compression.
-
A Comparison of Super-Resolution and Nearest Neighbors Interpolation Applied to Object Detection on Satellite Data
Nearest-neighbor interpolation matches multi-scale deep super-resolution performance for vehicle detection on 4x-upscaled xView satellite imagery, with a 0.0002 AP difference.