Thinking with Novel Views: A Systematic Analysis of Generative-Augmented Spatial Intelligence

• URL: http://arxiv.org/abs/2605.10588v1
• Date: Mon, 11 May 2026 13:59:09 GMT
• Title: Thinking with Novel Views: A Systematic Analysis of Generative-Augmented Spatial Intelligence
• Abstract summary: Thinking with Novel Views (TwNV) is a paradigm that integrates generative novel-view synthesis into the reasoning loop.<n>We show that TwNV consistently improves accuracy by +1.3 to +3.9 pp, with the largest gains on viewpoint-sensitive subtasks.
• Score: 60.11188590947511
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Current Large Multimodal Models (LMMs) struggle with spatial reasoning tasks requiring viewpoint-dependent understanding, largely because they are confined to a single, static observation. We propose Thinking with Novel Views (TwNV), a paradigm that integrates generative novel-view synthesis into the reasoning loop: a Reasoner LMM identifies spatial ambiguity, instructs a Painter to synthesize an alternative viewpoint, and re-examines the scene with the additional evidence. Through systematic experiments we address three research questions. (1) Instruction format: numerical camera-pose specifications yield more reliable view control than free-form language. (2) Generation fidelity: synthesized view quality is tightly coupled with downstream spatial accuracy. (3) Inference-time visual scaling: iterative multi-turn view refinement further improves performance, echoing recent scaling trends in language reasoning. Across four spatial subtask categories and four LMM architectures (both closed- and open-source), TwNV consistently improves accuracy by +1.3 to +3.9 pp, with the largest gains on viewpoint-sensitive subtasks. These results establish novel-view generation as a practical lever for advancing spatial intelligence of LMMs.

Related papers

• Symbolic and Abstractive Reasoning with Complex Visual Queries [57.59111649292774]
  We explore a novel abstract data type termed complex visual query (CVQ)<n>CVQ probes symbolic and abstractive reasoning, which is a critical yet underexplored dimension of human-like neuro-symbolic reasoning for MLLMs.<n>We introduce a two-stage training framework that progressively equips MLLMs with robust visual reasoning capabilities.
  arXiv  Detail & Related papers  (2026-06-08T08:30:51Z)
• LanteRn: Latent Visual Structured Reasoning [7.141402207573525]
  We introduce LanteRn, a framework that enables visual reasoning to occur directly in latent space.<n>LanteRn augments a vision-language transformer with the ability to generate and attend to continuous visual thought embeddings during inference.<n>We evaluate LanteRn on three perception-centric benchmarks (VisCoT, V*, and Blink)
  arXiv  Detail & Related papers  (2026-03-26T16:41:59Z)
• DiffThinker: Towards Generative Multimodal Reasoning with Diffusion Models [40.38351627330629]
  We introduce DiffThinker, a generative multimodal reasoning framework.<n>We show it can achieve superior logical consistency and spatial precision in vision-centric tasks.
  arXiv  Detail & Related papers  (2025-12-30T11:51:18Z)
• MPCAR: Multi-Perspective Contextual Augmentation for Enhanced Visual Reasoning in Large Vision-Language Models [7.702194892874595]
  Multi-Perspective Contextual Augmentation for Reasoning (MPCAR) is a novel inference-time strategy designed to enhance Large Vision-Language Models (LVLMs)<n>MPCAR operates in three stages: first, an LVLM generates N diverse and complementary descriptions or preliminary reasoning paths from various angles; second, these descriptions are intelligently integrated with the original question to construct a comprehensive context-augmented prompt; and finally, this enriched prompt guides the ultimate LVLM for deep reasoning and final answer generation.
  arXiv  Detail & Related papers  (2025-08-17T15:25:01Z)
• Unfolding Spatial Cognition: Evaluating Multimodal Models on Visual Simulations [61.235500325327585]
  Existing AI benchmarks primarily assess verbal reasoning, neglecting the complexities of non-verbal, multi-step visual simulation.<n>We introduce STARE, a benchmark designed to rigorously evaluate multimodal large language models on tasks better solved through visual simulation.<n>Our evaluations show that models excel at reasoning over simpler 2D transformations, but perform close to random chance on more complex tasks.
  arXiv  Detail & Related papers  (2025-06-05T05:09:46Z)
• 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)
• MMPerspective: Do MLLMs Understand Perspective? A Comprehensive Benchmark for Perspective Perception, Reasoning, and Robustness [50.33343842822694]
  We introduce MMPerspective, the first benchmark specifically designed to evaluate multimodal large language models' understanding of perspective.<n>Our benchmark comprises 2,711 real-world and synthetic image instances with 5,083 question-answer pairs that probe key capabilities.<n>Through a comprehensive evaluation of 43 state-of-the-art MLLMs, we uncover significant limitations.
  arXiv  Detail & Related papers  (2025-05-26T18:20:22Z)
• VOILA: Evaluation of MLLMs For Perceptual Understanding and Analogical Reasoning [63.0285363282581]
  Multimodal Large Language Models (MLLMs) have become a powerful tool for integrating visual and textual information.<n>We introduce VOILA, a benchmark designed to evaluate MLLMs' perceptual understanding and abstract relational reasoning.<n>We reveal that current MLLMs struggle to comprehend inter-image relationships and exhibit limited capabilities in high-level relational reasoning.
  arXiv  Detail & Related papers  (2025-02-25T23:36:19Z)

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.