The Earth in One Gaze: Training-Free Active Focus for UHR Remote Sensing Understanding

arXiv:2609.31747 · cs.CV, eess.IV · Submitted 2026-09-23 · Read on arXiv

cs.CV, eess.IV

Submitted: 2026-09-23

Updated: 2026-09-23

Code: https://github.com/zhangyyy-ai-rs/GazeEarth

Terminology

• Benchmark — 71× in this paper · explained in 2 episodes
• Accuracy — 56× in this paper · explained in 1 episode
• Alignment — 22× in this paper · explained in 1 episode
• Trace — 7× in this paper · explained in 2 episodes
• International Conference on Learning Representations — 5× in this paper
• Active Perception — 4× in this paper · explained in 2 episodes
• Conference on Computer Vision and Pattern Recognition — 4× in this paper
• Ablation — 3× in this paper · explained in 1 episode
• Active Vision — 3× in this paper · explained in 1 episode
• Frozen model — 3× in this paper · explained in 3 episodes
• Grounding — 3× in this paper · explained in 3 episodes
• Training-Free Framework — 3× in this paper · explained in 2 episodes
• Ablation study — 2× in this paper · explained in 1 episode
• Complex Reasoning — 2× in this paper
• Core — 2× in this paper · explained in 2 episodes
• Object Properties — 2× in this paper
• Provenance — 2× in this paper · explained in 3 episodes
• Redundancy — 2× in this paper · explained in 2 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Scene Classification — 2× in this paper
• Ablation Studies — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Hallucination — 1× in this paper · explained in 3 episodes
• Object Spatial Relationship — 1× in this paper
• Pruning — 1× in this paper · explained in 4 episodes
• RAG — 1× in this paper · explained in 3 episodes
• Semantic Understanding — 1× in this paper · explained in 2 episodes
• Spatiotemporal Reasoning — 1× in this paper

Sources

• Qwen2.5-VL Technical Report
• Qwen3-VL Technical Report
• Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
• CogVLM2: Visual Language Models for Image and Video Understanding
• Seeing Clearly without Training: Mitigating Hallucinations in Multimodal LLMs for Remote Sensing
• WeaveEarth: Structured Evidence Construction and Reasoning for Training-Free UHR Remote Sensing Understanding
• FOVEA: Foveated Image Magnification for Autonomous Navigation
• Learning to Zoom and Unzoom
• SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
• Text Before Vision: Staged Knowledge Injection Matters for Agentic RLVR in Ultra-High-Resolution Remote Sensing Understanding
• Towards Perceiving Small Visual Details in Zero-shot Visual Question Answering with Multimodal LLMs
• Look Where It Matters: Training-Free Ultra-HR Remote Sensing VQA via Adaptive Zoom Search

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models