Contextual Observer Grounding: Evaluating Situated Spatial Reasoning in Vision-Language Models

• URL: http://arxiv.org/abs/2609.06880v1
• Date: Mon, 07 Sep 2026 00:00:13 GMT
• Title: Contextual Observer Grounding: Evaluating Situated Spatial Reasoning in Vision-Language Models
• Abstract summary: Reasoning over language instructions in embodied tasks often requires understanding spatial relations from a speaker's situated perspective.<n>Recent vision-language models (VLMs) appear capable of spatial reasoning, but their ability to infer a speaker's viewpoint from contextual cues remains unclear.
• Score: 22.823647299309712
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reasoning over language instructions in embodied tasks such as robotics often requires understanding spatial relations from a speaker's situated perspective. Humans infer such perspectives from shared environmental knowledge, activity context, and commonsense. Recent vision-language models (VLMs) appear capable of spatial reasoning, but their ability to infer a speaker's viewpoint from contextual cues and interpret situated spatial relations from that viewpoint remains unclear. We call this capability contextual observer grounding. To study this capability, we construct the Point-of-View Benchmark (POVBench), a dataset of 3D scenes and queries that disentangles Inferred, Stated, and Given forms of observer grounding in natural embodied communication. Given multi-view observations and a natural-language sentence, models must localize unseen or underspecified targets from situated spatial and contextual cues. Across state-of-the-art VLMs, localizing targets from directional language remains challenging, even when observer grounding is made explicit. We find that explicit breakdowns of observer-relative spatial reasoning improve target localization. Our project page is available at https://mimo-owl.github.io/POVBench/.

Related papers

• Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models [61.89854422423702]
  Vision language models (VLMs) excel at many tasks but struggle with spatial reasoning when critical information is not directly observable.<n>We introduce Imaginative Perception Tokens (IPT), intermediate perceptual representations that externalize what a VLM would perceive under alternative spatial configurations.<n>IPT supervision consistently improves spatial reasoning and often outperforms textual chain of thought training.
  arXiv  Detail & Related papers  (2026-06-02T17:59:17Z)
• SpatialImaginer: Towards Adaptive Visual Imagination for Spatial Reasoning [67.67774742200626]
  spatial intelligence, which refers to the ability to reason about geometric and physical structure from visual observations, is a core challenge for large language models.<n>We propose a unified multimodal generation framework that integrates textual reasoning with visual imagination.<n>Our framework adopts a divide-and-conquer strategy, using text chain-of-thought for high-level semantic planning and the visual imagination for geometry-sensitive state transformation and consistency preservation.
  arXiv  Detail & Related papers  (2026-04-19T11:21:59Z)
• Referring Expressions as a Lens into Spatial Language Grounding in Vision-Language Models [22.672848927658958]
  We propose using the Referring Expression task as a platform for the evaluation of spatial reasoning by Vision-language models (VLMs)<n>This platform provides the opportunity for a deeper analysis of spatial comprehension and grounding abilities when there is 1) ambiguity in object detection, 2) complex spatial expressions with a longer sentence structure and multiple spatial relations, and 3) expressions with negation ('not')<n>Our results highlight these challenges and behaviors and provide insight into research gaps and future directions.
  arXiv  Detail & Related papers  (2025-11-08T21:43:09Z)
• Spatial Reasoning in Foundation Models: Benchmarking Object-Centric Spatial Understanding [8.202861909913791]
  We present a benchmark for object-centric spatial reasoning in foundation models.<n>We find a stable trade-off: detectors such as GroundingDINO and OWLv2 deliver precise boxes with limited relational reasoning.<n>Our study highlights the gap between localization and true spatial understanding, and pointing toward the need for spatially-aware foundation models in the community.
  arXiv  Detail & Related papers  (2025-09-26T06:06:19Z)
• A Neural Representation Framework with LLM-Driven Spatial Reasoning for Open-Vocabulary 3D Visual Grounding [78.99798110890157]
  Open-vocabulary 3D visual grounding aims to localize target objects based on free-form language queries.<n>Existing language field methods struggle to accurately localize instances using spatial relations in language queries.<n>We propose SpatialReasoner, a novel neural representation-based framework with large language model (LLM)-driven spatial reasoning.
  arXiv  Detail & Related papers  (2025-07-09T10:20:38Z)
• 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)
• Language Conditioned Spatial Relation Reasoning for 3D Object Grounding [87.03299519917019]
  Localizing objects in 3D scenes based on natural language requires understanding and reasoning about spatial relations. We propose a language-conditioned transformer model for grounding 3D objects and their spatial relations.
  arXiv  Detail & Related papers  (2022-11-17T16:42:39Z)
• LanguageRefer: Spatial-Language Model for 3D Visual Grounding [72.7618059299306]
  We develop a spatial-language model for a 3D visual grounding problem. We show that our model performs competitively on visio-linguistic datasets proposed by ReferIt3D.
  arXiv  Detail & Related papers  (2021-07-07T18:55:03Z)
• Spatial Language Understanding for Object Search in Partially Observed Cityscale Environments [21.528770932332474]
  We introduce the spatial language observation space and formulate a model under the framework of Partially Observable Markov Decision Process (POMDP) We propose a convolutional neural network model that learns to predict the language provider's relative frame of reference (FoR) given environment context. We demonstrate the generalizability of our FoR prediction model and object search system through cross-validation over areas of five cities, each with a 40,000m$2$ footprint.
  arXiv  Detail & Related papers  (2020-12-04T16:27:59Z)

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.