GeoHeight-Bench: Towards Height-Aware Multimodal Reasoning in Remote Sensing

• URL: http://arxiv.org/abs/2603.25565v1
• Date: Thu, 26 Mar 2026 15:38:02 GMT
• Title: GeoHeight-Bench: Towards Height-Aware Multimodal Reasoning in Remote Sensing
• Abstract summary: We introduce a comprehensive evaluation framework dedicated to height-aware remote sensing understanding.<n>We develop a scalable, VLM-driven data generation pipeline utilizing systematic prompt engineering and metadata extraction.<n>To validate the necessity of height perception, we propose GeoHeightChat, the first height-aware remote sensing LMM baseline.
• Score: 15.118294966433401
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Current Large Multimodal Models (LMMs) in Earth Observation typically neglect the critical "vertical" dimension, limiting their reasoning capabilities in complex remote sensing geometries and disaster scenarios where physical spatial structures often outweigh planar visual textures. To bridge this gap, we introduce a comprehensive evaluation framework dedicated to height-aware remote sensing understanding. First, to overcome the severe scarcity of annotated data, we develop a scalable, VLM-driven data generation pipeline utilizing systematic prompt engineering and metadata extraction. This pipeline constructs two complementary benchmarks: GeoHeight-Bench for relative height analysis, and a more challenging GeoHeight-Bench+ for holistic, terrain-aware reasoning. Furthermore, to validate the necessity of height perception, we propose GeoHeightChat, the first height-aware remote sensing LMM baseline. Serving as a strong proof of concept, our baseline demonstrates that synergizing visual semantics with implicitly injected height geometric features effectively mitigates the "vertical blind spot", successfully unlocking a new paradigm of interactive height reasoning in existing optical models.

Related papers

• VGP-Nav: Metric-Aware Visual Geometric Perception for Robot Navigation [59.44896676402453]
  VGP-Nav is a unified framework for textitMetric-Aware Visual Geometric Perception<n>It relies solely on monocular RGB input to jointly support metric localization and obstacle perception.<n>VGP-Nav resolves monocular scale ambiguity online and produces localization-grounded, metric obstacle representations.
  arXiv  Detail & Related papers  (2026-06-08T09:38:14Z)
• LiAuto-GeoX: Efficient Grounded Driving Transformer [54.23823436153608]
  We present textbfLiAuto-GeoX, an efficient grounded driving transformer for deployable, ego-centric 3D scene understanding.<n>We show that textbfLiAuto-GeoX runs at 220 FPS on KITTI while maintaining high-fidelity dense reconstruction, enabling real-time deployment.
  arXiv  Detail & Related papers  (2026-06-04T06:58:44Z)
• GeoSense: Internalizing Geometric Necessity Perception for Multimodal Reasoning [51.63457948949102]
  We develop a framework to overcome the limited spatial understanding of Multimodal Large Language Models (MLLMs)<n>Our framework endows the model with an awareness of perceptual insufficiency, empowering it to autonomously engage geometric features in reasoning when 2D cues are deemed insufficient.
  arXiv  Detail & Related papers  (2026-03-11T03:32:12Z)
• FGAA-FPN: Foreground-Guided Angle-Aware Feature Pyramid Network for Oriented Object Detection [1.0152838128195467]
  We propose a Foreground-Guided Angle-Aware Feature Pyramid Network for oriented object detection.<n> FGAA-FPN is built on a hierarchical functional decomposition that accounts for the distinct spatial resolution and semantic abstraction across pyramid levels.<n>Experiments on DOTA v1.0 and DOTA v1.5 demonstrate that FGAA-FPN state-of-the-art results, reaching 75.5% and 68.3% mAP, respectively.
  arXiv  Detail & Related papers  (2026-02-11T10:15:06Z)
• Thinking with Geometry: Active Geometry Integration for Spatial Reasoning [68.59084007360615]
  We propose GeoThinker, a framework that shifts paradigm passive fusion to active perception.<n>Instead of feature mixing, GeoThinker enables the model to selectively retrieve geometric evidence conditioned on its internal reasoning demands.<n>Our results indicate that the ability to actively integrate spatial structures is essential for next-generation spatial intelligence.
  arXiv  Detail & Related papers  (2026-02-05T18:59:32Z)
• Dynamic Topology Awareness: Breaking the Granularity Rigidity in Vision-Language Navigation [22.876516699004814]
  Vision-Language Navigation in Continuous Environments (VLN-CE) presents a core challenge: grounding high-level linguistic instructions into precise, safe, and long-horizon spatial actions.<n>Explicit topological maps have proven to be a vital solution for providing robust spatial memory in such tasks.<n>Existing topological planning methods suffer from a "Granularity Rigidity" problem.<n>We propose DGNav, a framework for Dynamic Topological Navigation, introducing a context-aware mechanism to modulate map density and connectivity on-the-fly.
  arXiv  Detail & Related papers  (2026-01-29T14:06:23Z)
• Towards Scalable Foundation Model for Multi-modal and Hyperspectral Geospatial Data [14.104497777255137]
  We introduce Low-rank Efficient Spatial-Spectral Vision Transformer with three key innovations.<n>We pretrain LESS ViT using a Hyperspectral Masked Autoencoder framework with integrated positional and channel masking strategies.<n> Experimental results demonstrate that our proposed method achieves competitive performance against state-of-the-art multi-modal geospatial foundation models.
  arXiv  Detail & Related papers  (2025-03-17T05:42:19Z)
• Understanding Depth and Height Perception in Large Visual-Language Models [21.209275651704758]
  We focus on evaluating the geometric understanding of Vision Language Models (VLMs)<n>We find that although they excel in perceiving basic geometric properties like shape and size, they consistently struggle with depth and height perception.<n>This study aims to pave the way for developing VLMs with enhanced geometric understanding.
  arXiv  Detail & Related papers  (2024-08-21T16:16:18Z)
• GeoLRM: Geometry-Aware Large Reconstruction Model for High-Quality 3D Gaussian Generation [65.33726478659304]
  We introduce the Geometry-Aware Large Reconstruction Model (GeoLRM), an approach which can predict high-quality assets with 512k Gaussians and 21 input images in only 11 GB GPU memory. Previous works neglect the inherent sparsity of 3D structure and do not utilize explicit geometric relationships between 3D and 2D images. GeoLRM tackles these issues by incorporating a novel 3D-aware transformer structure that directly processes 3D points and uses deformable cross-attention mechanisms.
  arXiv  Detail & Related papers  (2024-06-21T17:49:31Z)
• HeightFormer: A Multilevel Interaction and Image-adaptive Classification-regression Network for Monocular Height Estimation with Aerial Images [10.716933766055755]
  This paper presents a comprehensive solution for monocular height estimation in remote sensing. It features the Multilevel Interaction Backbone (MIB) and Image-adaptive Classification-regression Height Generator (ICG) The ICG dynamically generates height partition for each image and reframes the traditional regression task.
  arXiv  Detail & Related papers  (2023-10-12T02:49:00Z)
• DepthFormer: Exploiting Long-Range Correlation and Local Information for Accurate Monocular Depth Estimation [50.08080424613603]
  Long-range correlation is essential for accurate monocular depth estimation. We propose to leverage the Transformer to model this global context with an effective attention mechanism. Our proposed model, termed DepthFormer, surpasses state-of-the-art monocular depth estimation methods with prominent margins.
  arXiv  Detail & Related papers  (2022-03-27T05:03:56Z)
• Disentangled Latent Transformer for Interpretable Monocular Height Estimation [15.102260054654923]
  We study how deep neural networks predict height from a single monocular image. Our work provides novel insights for both understanding and designing MHE models.
  arXiv  Detail & Related papers  (2022-01-17T11:42:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.