VIEW2SPACE: Studying Multi-View Visual Reasoning from Sparse Observations

• URL: http://arxiv.org/abs/2603.16506v2
• Date: Wed, 18 Mar 2026 04:22:15 GMT
• Title: VIEW2SPACE: Studying Multi-View Visual Reasoning from Sparse Observations
• Abstract summary: Multi-view visual reasoning is essential for intelligent systems that must understand complex environments from sparse and discrete viewpoints.<n>In real-world scenarios, reasoning across views requires integrating partial observations without explicit guidance.<n>We leverage physically grounded simulation to construct diverse, high-fidelity 3D scenes with precise per-view metadata.
• Score: 47.94531550391802
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multi-view visual reasoning is essential for intelligent systems that must understand complex environments from sparse and discrete viewpoints, yet existing research has largely focused on single-image or temporally dense video settings. In real-world scenarios, reasoning across views requires integrating partial observations without explicit guidance, while collecting large-scale multi-view data with accurate geometric and semantic annotations remains challenging. To address this gap, we leverage physically grounded simulation to construct diverse, high-fidelity 3D scenes with precise per-view metadata, enabling scalable data generation that remains transferable to real-world settings. Based on this engine, we introduce VIEW2SPACE, a multi-dimensional benchmark for sparse multi-view reasoning, together with a scalable, disjoint training split supporting millions of grounded question-answer pairs. Using this benchmark, a comprehensive evaluation of state-of-the-art vision-language and spatial models reveals that multi-view reasoning remains largely unsolved, with most models performing only marginally above random guessing. We further investigate whether training can bridge this gap. Our proposed Grounded Chain-of-Thought with Visual Evidence substantially improves performance under moderate difficulty, and generalizes to real-world data, outperforming existing approaches in cross-dataset evaluation. We further conduct difficulty-aware scaling analyses across model size, data scale, reasoning depth, and visibility constraints, indicating that while geometric perception can benefit from scaling under sufficient visibility, deep compositional reasoning across sparse views remains a fundamental challenge.

Related papers

• MultiView-Bench: A Diagnostic Benchmark for World-Centric Multi-View Integration in VLMs [40.317798580235]
  Recent benchmarks for VLMs largely assess single- or limited-view perception, leaving untested the core cognitive ability to integrate observations across viewpoints into a coherent, world-centric (allocentric) 3D mental model.<n>We introduce MultiView-Bench, a diagnostic benchmark expressly designed to evaluate multi-view integration for holistic 3D scene comprehension.<n>We propose ViewNavigator, a multi-agent framework that actively selects informative viewpoints, perceives, and fuses multi-view evidence, improving diverse base models on MultiView-Bench even under a strict budget-matched comparison.
  arXiv  Detail & Related papers  (2026-07-09T22:22:42Z)
• Diversity-aware View Partitioning for Scalable VGGT [48.654660686945526]
  VGGT achieve strong performance by jointly reasoning over multiple views with global attention.<n>We propose a training-free and plug-and-play inference framework that organizes views into diversity-aware balanced chunks.<n>Our framework also complements existing VGGT variants, enabling scalable multi-view reconstruction without sacrificing geometric fidelity.
  arXiv  Detail & Related papers  (2026-07-02T08:37:56Z)
• 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)
• Perception-Aware Multimodal Spatial Reasoning from Monocular Images [57.42071289037214]
  spatial reasoning from monocular images is essential for autonomous driving.<n>Current Vision-Language Models (VLMs) still struggle with fine-grained geometric perception.<n>We propose a perception-aware multimodal reasoning framework that equipsVLMs with explicit object-centric grounding ability.
  arXiv  Detail & Related papers  (2026-03-07T02:05:12Z)
• SpatialMosaic: A Multiview VLM Dataset for Partial Visibility [25.874299974251965]
  We propose a scalable multi-view data generation and annotation pipeline that constructs realistic spatial reasoning QAs.<n>We introduce SpatialMosaic-Bench, a benchmark for evaluating multi-view spatial reasoning under realistic and challenging scenarios.<n>We also present SpatialMosaicVLM, a hybrid framework that integrates 3D reconstruction models as geometry encoders within Vision-Language Models.
  arXiv  Detail & Related papers  (2025-12-29T10:48:54Z)
• Reasoning Path and Latent State Analysis for Multi-view Visual Spatial Reasoning: A Cognitive Science Perspective [17.592210658831902]
  spatial reasoning is a core aspect of human intelligence that allows perception, inference and planning in 3D environments.<n>Current vision-language models (VLMs) struggle to maintain geometric coherence and cross-view consistency for spatial reasoning in multi-view settings.<n>We present ReMindView-Bench, a cognitively grounded benchmark for evaluating how VLMs construct, align and maintain spatial mental models across complementary viewpoints.
  arXiv  Detail & Related papers  (2025-12-02T02:21:29Z)
• Multimodal Spatial Reasoning in the Large Model Era: A Survey and Benchmarks [108.15756345836901]
  We provide a comprehensive review of multimodal spatial reasoning tasks with large models.<n>We review advances in embodied AI, including vision-language navigation and action models.<n>We consider emerging modalities such as audio and egocentric video, which contribute to novel spatial understanding through new sensors.
  arXiv  Detail & Related papers  (2025-10-29T17:55:43Z)
• 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)
• Partial Multi-View Clustering via Meta-Learning and Contrastive Feature Alignment [13.511433241138702]
  Partial multi-view clustering (PVC) presents significant challenges practical research problem for data analysis in real-world applications. Existing clustering methods struggle to handle incomplete views effectively, leading to suboptimal clustering performance. We propose a novel dual optimization framework based on contrastive learning, which aims to maximize the consistency of latent features in incomplete multi-view data.
  arXiv  Detail & Related papers  (2024-11-14T19:16:01Z)
• Hierarchical Mutual Information Analysis: Towards Multi-view Clustering in The Wild [9.380271109354474]
  This work proposes a deep MVC framework where data recovery and alignment are fused in a hierarchically consistent way to maximize the mutual information among different views. To the best of our knowledge, this could be the first successful attempt to handle the missing and unaligned data problem separately with different learning paradigms.
  arXiv  Detail & Related papers  (2023-10-28T06:43:57Z)
• A Variational Information Bottleneck Approach to Multi-Omics Data Integration [98.6475134630792]
  We propose a deep variational information bottleneck (IB) approach for incomplete multi-view observations. Our method applies the IB framework on marginal and joint representations of the observed views to focus on intra-view and inter-view interactions that are relevant for the target. Experiments on real-world datasets show that our method consistently achieves gain from data integration and outperforms state-of-the-art benchmarks.
  arXiv  Detail & Related papers  (2021-02-05T06:05:39Z)
• Agglomerative Neural Networks for Multi-view Clustering [109.55325971050154]
  We propose the agglomerative analysis to approximate the optimal consensus view. We present Agglomerative Neural Network (ANN) based on Constrained Laplacian Rank to cluster multi-view data directly. Our evaluations against several state-of-the-art multi-view clustering approaches on four popular datasets show the promising view-consensus analysis ability of ANN.
  arXiv  Detail & Related papers  (2020-05-12T05:39:10Z)

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.