arXiv Computer Vision
GeoDIVE: Geospatial Descent Informed by Value Estimation
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
Aug 27
GTPred: Benchmarking MLLMs for Interpretable Geo-localization and Time-of-capture Prediction
GTPred is a new benchmark for geo‑temporal prediction that evaluates multi‑modal large language models (MLLMs) on 370 images taken across 120 years worldwide. It assesses predictions by matching both the year and a hierarchical location sequence, and includes annotated reasoning chains to test intermediate reasoning. Experiments on 15 MLLMs show that while visual perception is strong, models still lack world knowledge and geo‑temporal reasoning, and that adding temporal data improves location inference.
Hugging Face Trending Papers
Sep 2
Genesis: A Generative Engine for Hierarchical Satellite Image Synthesis
Genesis is a generative engine designed to synthesize complete, globally consistent quadtree pyramids for satellite imagery. It tackles the new multi‑scale tile completion task by combining a vertical super‑resolution model with a horizontal mask‑based outpainting model, enabling seamless generation across arbitrary zoom levels and positions. The authors also release dense500, a fully observed multi‑scale dataset, and a suite of pyramid‑level metrics to benchmark performance.
arXiv Computer Vision
Sep 3
Genesis: A Generative Engine for Hierarchical Satellite Image Synthesis
Genesis is a generative engine that produces fully consistent multi‑scale satellite image pyramids by combining a vertical super‑resolution model with a horizontal mask‑based outpainting model. It addresses the lack of existing methods that can synthesize a complete quadtree from sparse seed tiles at arbitrary zoom levels and positions, ensuring coherence across both scale and space. The authors also release dense500, a comprehensive multi‑scale dataset and evaluation suite, to benchmark this new task.
arXiv AI
Jun 30
Multimodal and Multiscale Spatial-Temporal Semantic Search and Recommendation with AI Foundation Models
arXiv:2606. 28369v1 Announce Type: cross Abstract: Semantic search and recommendation of similar documents, such as news and reports about unusual environmental events (e.
arXiv AI
Jul 15
Weakly Supervised Spatio-Temporal Candidate Discovery of Dairy Farm Sites from Seasonal Satellite Imagery
arXiv:2607. 12748v1 Announce Type: cross Abstract: Farm site discovery from satellite imagery is a spatiotemporal candidate ranking problem because farm evidence is distributed across pasture, field boundaries, roads, buildings, and seasonal vegetation patterns.
arXiv Computer Vision
Sep 24
VLM2GeoVec: Toward Universal Multimodal Embeddings for Remote Sensing
The paper introduces RSMEB, a unified benchmark for remote‑sensing multimodal retrieval that evaluates both cross‑modal and interleaved retrieval across 21 tasks under a single ranking protocol. It also presents VLM2GeoVec, an instruction‑conditioned single‑encoder model that embeds image, text, bounding‑box, and geo‑coordinate tokens into one sequence and achieves state‑of‑the‑art performance on region‑caption, referring‑expression, and semantic geo‑aware retrieval while remaining competitive on conventional tasks. The authors provide code, checkpoints, and data on GitHub to facilitate reproducibility.