CaMo: Camera Motion Grounded Evaluation and Training for Vision-Language Models

• URL: http://arxiv.org/abs/2605.20165v1
• Date: Tue, 19 May 2026 17:50:25 GMT
• Title: CaMo: Camera Motion Grounded Evaluation and Training for Vision-Language Models
• Abstract summary: Vision-Language Models (VLMs) achieve strong performance on spatial question answering benchmarks.<n>But it remains unclear whether such gains reflect genuine spatial intelligence.<n>We show that existing spatial VLMs lack basic camera motion understanding.<n>We introduce CaMo, a camera motion grounded VLM that achieves consistent performance across SNS evaluation and direct spatial question answering accuracy.
• Score: 27.555254461854133
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision-Language Models (VLMs) achieve strong performance on spatial question answering benchmarks, yet it remains unclear whether such gains reflect genuine spatial intelligence. We show that existing spatial VLMs lack basic camera motion understanding, a key component of spatial cognition. We propose the Spatial Narrative Score (SNS), an evaluation framework that requires VLMs to generate explicit spatial narratives capturing both scene semantics and camera motion, followed by reasoning with a frozen proxy LLM. Under SNS, state-of-the-art spatial VLMs exhibit significant performance degradation despite high direct question answering accuracy. To address this gap, we introduce CaMo, a camera motion grounded VLM that achieves consistent performance across SNS evaluation and direct spatial question answering accuracy. Our results highlight the importance of explicit spatial narrative externalization for evaluating VLMs with transferable 3D spatial understanding. Our code, data, and model is available at https://github.com/hsiangwei0903/CaMo

Related papers

• SpatioLM: Towards General Physical Spatial Intelligence in Vision-Language Models [19.19065314413351]
  We propose a parameter-efficient textittextbfSpatio-vision textbfLanguage bftextModels (SpatioLM), that enhances spatial intelligence without extra 3D prior inputs or third-party spatial encoders.<n>We design a plug-and-play and non-invasive-vision module that elicits the spatial knowledge inherent in VLMs.<n>Experiments show that SpatioLM achieves significant improvements in diverse tasks, including spatial perception and understanding.
  arXiv  Detail & Related papers  (2026-08-03T08:36:18Z)
• SIMS-V: Simulated Instruction-Tuning for Spatial Video Understanding [64.86119288520419]
  multimodal language models struggle with spatial reasoning across time and space.<n>We present SIMS-V -- a systematic data-generation framework that leverages the privileged information of 3D simulators.<n>Our approach demonstrates robust generalization, maintaining performance on general video understanding while showing substantial improvements on embodied and real-world spatial tasks.
  arXiv  Detail & Related papers  (2025-11-06T18:53:31Z)
• SD-VLM: Spatial Measuring and Understanding with Depth-Encoded Vision-Language Models [75.64836077468722]
  Vision language models (VLMs) excel in 2D semantic visual understanding, but their ability to quantitatively reason about 3D spatial relationships remains under-explored.<n>We propose SD-VLM, a novel framework that significantly enhances fundamental spatial perception abilities of VLMs.<n>We have trained SD-VLM, a strong generalist VLM which shows superior quantitative spatial measuring and understanding capability.
  arXiv  Detail & Related papers  (2025-09-22T12:08:12Z)
• Understanding Space Is Rocket Science -- Only Top Reasoning Models Can Solve Spatial Understanding Tasks [9.23437069873238]
  We propose an open-source contrastive VLM benchmark that tests for spatial relation understanding.<n>RocketScience is comprised of entirely new real-world image-text pairs.<n>Results show a striking lack of spatial relation understanding in open source and frontier commercial VLMs.
  arXiv  Detail & Related papers  (2025-09-02T10:32:58Z)
• LRR-Bench: Left, Right or Rotate? Vision-Language models Still Struggle With Spatial Understanding Tasks [22.011855291417856]
  It remains underexplored how Vision-Language Models (VLMs) recognize spatial relationships and perceive spatial movement.<n>In this work, we introduce a spatial evaluation pipeline and construct a corresponding benchmark.<n>We conduct experiments on multiple state-of-the-art VLMs and observe that there is significant room for improvement.
  arXiv  Detail & Related papers  (2025-07-27T08:31:24Z)
• SIRI-Bench: Challenging VLMs' Spatial Intelligence through Complex Reasoning Tasks [51.774165536666864]
  We introduce SIRI-Bench, a benchmark designed to evaluate Vision-Language Models' structural spatial intelligence.<n>Bench comprises 9,000 video-question-answer triplets, where each problem is embedded in a realistic 3D scene.<n> Experimental results reveal that state-of-the-art VLMs struggle significantly on SIRI-Bench, underscoring the challenge of structural spatial reasoning.
  arXiv  Detail & Related papers  (2025-06-17T13:40:00Z)
• ViewSpatial-Bench: Evaluating Multi-perspective Spatial Localization in Vision-Language Models [68.46716645478661]
  Vision-language models (VLMs) have demonstrated remarkable capabilities in understanding and reasoning about visual content.<n>Current VLMs excel primarily at egocentric spatial reasoning (from the camera's perspective) but fail to generalize to allocentric viewpoints.<n>We introduce ViewSpatial-Bench, the first comprehensive benchmark designed specifically for multi-viewpoint spatial localization recognition evaluation.
  arXiv  Detail & Related papers  (2025-05-27T17:59:26Z)
• Mind the Gap: Benchmarking Spatial Reasoning in Vision-Language Models [14.442394137843923]
  We present a detailed analysis that first delineates the core elements of spatial reasoning.<n>We then assesses the performance of these models in both synthetic and real-world images.
  arXiv  Detail & Related papers  (2025-03-25T14:34:06Z)
• Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas [69.56484419619919]
  We study the spatial reasoning challenge from the lens of mechanistic interpretability.<n>We observe that successful spatial reasoning correlates strongly with the model's ability to align its attention with actual object locations.<n>Motivated by these findings, we propose ADAPTVIS to sharpen the attention on highly relevant regions when confident.
  arXiv  Detail & Related papers  (2025-03-03T17:57:03Z)
• SpatialRGPT: Grounded Spatial Reasoning in Vision Language Models [68.13636352687257]
  We introduce Spatial Region GPT (SpatialRGPT) to enhance VLMs' spatial perception and reasoning capabilities. During inference, when provided with user-specified region proposals, SpatialRGPT can accurately perceive their relative directions and distances. Our results demonstrate that SpatialRGPT significantly enhances performance in spatial reasoning tasks, both with and without local region prompts.
  arXiv  Detail & Related papers  (2024-06-03T17:59:06Z)
• SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities [59.39858959066982]
  understanding and reasoning about spatial relationships is a fundamental capability for Visual Question Answering (VQA) and robotics. We develop an automatic 3D spatial VQA data generation framework that scales up to 2 billion VQA examples on 10 million real-world images. By training a VLM on such data, we significantly enhance its ability on both qualitative and quantitative spatial VQA.
  arXiv  Detail & Related papers  (2024-01-22T18:01:01Z)

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.