English
Related papers

Related papers: Beyond Flatlands: Unlocking Spatial Intelligence b…

200 papers

Vision language models (VLMs) can flexibly address various vision tasks through text interactions. Although successful in semantic understanding, state-of-the-art VLMs including GPT-5 still struggle in understanding 3D from 2D inputs. On…

Computer Vision and Pattern Recognition · Computer Science 2025-10-02 Zhipeng Cai , Ching-Feng Yeh , Hu Xu , Zhuang Liu , Gregory Meyer , Xinjie Lei , Changsheng Zhao , Shang-Wen Li , Vikas Chandra , Yangyang Shi

Understanding and reasoning about spatial relationships is a fundamental capability for Visual Question Answering (VQA) and robotics. While Vision Language Models (VLM) have demonstrated remarkable performance in certain VQA benchmarks,…

Computer Vision and Pattern Recognition · Computer Science 2024-01-23 Boyuan Chen , Zhuo Xu , Sean Kirmani , Brian Ichter , Danny Driess , Pete Florence , Dorsa Sadigh , Leonidas Guibas , Fei Xia

Current Large Language Models have achieved Olympiad-level logic, yet Vision-Language Models paradoxically falter on elementary spatial tasks like block counting. This capability mismatch reveals a critical ``spatial intelligence gap,''…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Shaoxiong Zhan , Yanlin Lai , Zheng Liu , Hai Lin , Shen Li , Xiaodong Cai , Zijian Lin , Wen Huang , Hai-Tao Zheng

Vision-Language Models (VLMs) have shown remarkable performance on diverse visual and linguistic tasks, yet they remain fundamentally limited in their understanding of 3D spatial structures. We propose Geometric Distillation, a lightweight,…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Seonho Lee , Jiho Choi , Inha Kang , Jiwook Kim , Junsung Park , Hyunjung Shim

Spatial reasoning, the ability to understand and interpret the 3D structure of the world, is a critical yet underdeveloped capability in Multimodal Large Language Models (MLLMs). Current methods predominantly rely on verbal descriptive…

Computer Vision and Pattern Recognition · Computer Science 2025-12-09 Meng Cao , Haokun Lin , Haoyuan Li , Haoran Tang , Rongtao Xu , Dong An , Xue Liu , Ian Reid , Xiaodan Liang

Geometric problem solving constitutes a critical branch of mathematical reasoning, requiring precise analysis of shapes and spatial relationships. Current evaluations of geometric reasoning in vision-language models (VLMs) face limitations,…

Computer Vision and Pattern Recognition · Computer Science 2026-01-01 Yuan Feng , Yue Yang , Xiaohan He , Jiatong Zhao , Jianlong Chen , Zijun Chen , Daocheng Fu , Qi Liu , Renqiu Xia , Bo Zhang , Junchi Yan

Spatial reasoning and visual grounding are core capabilities for vision-language models (VLMs), yet most medical VLMs produce predictions without transparent reasoning or spatial evidence. Existing benchmarks also evaluate VLMs on isolated…

Computer Vision and Pattern Recognition · Computer Science 2026-04-20 Lama Moukheiber , Caleb M. Yeung , Haotian Xue , Alec Helbling , Zelin Zhao , Yongxin Chen

Spatial reasoning over three-dimensional scenes is a core capability for embodied intelligence, yet continuous model improvement remains bottlenecked by the cost of geometric annotation. The self-evolving paradigm offers a promising path,…

Current Vision-Language Models (VLMs) fail at quantitative spatial reasoning because their architectures destroy pixel-level information required for counting and measurements. Vision encoders compress images through patch embeddings,…

Computer Vision and Pattern Recognition · Computer Science 2026-01-21 Peter A. Massih , Eric Cosatto

While contemporary Vision-Language Models (VLMs) excel at 2D visual understanding, they remain constrained by a passive, 2D-centric paradigm that severely limits genuine 3D spatial reasoning. To bridge this gap, we introduce Think3D, a…

Computer Vision and Pattern Recognition · Computer Science 2026-03-18 Zaibin Zhang , Yuhan Wu , Lianjie Jia , Yifan Wang , Zhongbo Zhang , Yijiang Li , Binghao Ran , Fuxi Zhang , Zhuohan Sun , Zhenfei Yin , Lijun Wang , Huchuan Lu

Spatial reasoning -- the ability to perceive and reason about relationships in space -- advances vision-language models (VLMs) from visual perception toward spatial semantic understanding. Existing approaches either revisit local image…

Computer Vision and Pattern Recognition · Computer Science 2026-01-06 Weijian Ma , Shizhao Sun , Tianyu Yu , Ruiyu Wang , Tat-Seng Chua , Jiang Bian

Recent advancements in Large Language Models (LLMs) and Vision-Language Models (VLMs) have made them powerful tools in embodied navigation, enabling agents to leverage commonsense and spatial reasoning for efficient exploration in…

While Multimodal Large Language Models (MLLMs) excel in semantic tasks, they frequently lack the "spatial sense" essential for sophisticated geometric reasoning. Current models typically suffer from exorbitant modality-alignment costs and…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Yi Zhang , Youya Xia , Yong Wang , Meng Song , Xin Wu , Wenjun Wan , Bingbing Liu , AiXue Ye , Hongbo Zhang , Feng Wen

Vision language models (VLMs) perform well on many tasks but often fail at spatial reasoning, which is essential for navigation and interaction with physical environments. Many spatial reasoning tasks depend on fundamental two-dimensional…

Computer Vision and Pattern Recognition · Computer Science 2025-10-03 Yihong Tang , Ao Qu , Zhaokai Wang , Dingyi Zhuang , Zhaofeng Wu , Wei Ma , Shenhao Wang , Yunhan Zheng , Zhan Zhao , Jinhua Zhao

Current Visual-Language Navigation (VLN) methodologies face a trade-off between semantic understanding and control precision. While Multimodal Large Language Models (MLLMs) offer superior reasoning, deploying them as low-level controllers…

Robotics · Computer Science 2026-02-19 Zhenxing Xu , Brikit Lu , Weidong Bao , Zhengqiu Zhu , Junsong Zhang , Hui Yan , Wenhao Lu , Ji Wang

The significance of cross-view 3D geometric modeling capabilities for autonomous driving is self-evident, yet existing Vision-Language Models (VLMs) inherently lack this capability, resulting in their mediocre performance. While some…

Computer Vision and Pattern Recognition · Computer Science 2026-02-25 Jie Wang , Guang Li , Zhijian Huang , Chenxu Dang , Hangjun Ye , Yahong Han , Long Chen

Advancing towards artificial superintelligence requires rich and intelligent perceptual capabilities. A critical frontier in this pursuit is overcoming the limited spatial understanding of Multimodal Large Language Models (MLLMs), where…

Computer Vision and Pattern Recognition · Computer Science 2026-03-12 Ruiheng Liu , Haihong Hao , Mingfei Han , Xin Gu , Kecheng Zhang , Changlin Li , Xiaojun Chang

Benchmarking spatial reasoning in multimodal large language models (MLLMs) has attracted growing interest in computer vision due to its importance for embodied AI and other agentic systems that require precise interaction with the physical…

Computer Vision and Pattern Recognition · Computer Science 2026-02-19 Zelin Xu , Yupu Zhang , Saugat Adhikari , Saiful Islam , Tingsong Xiao , Zibo Liu , Shigang Chen , Da Yan , Zhe Jiang

While Vision-Language Models (VLMs) are set to transform robotic navigation, existing methods often underutilize their reasoning capabilities. To unlock the full potential of VLMs in robotics, we shift their role from passive observers to…

Robotics · Computer Science 2025-11-13 Mobin Habibpour , Fatemeh Afghah

Vision-Language Models (VLMs) excel at 2D tasks such as grounding and captioning, yet remain limited in 3D understanding. A key limitation is their text-only supervision paradigm, which under-constrains fine-grained visual perception and…

Computer Vision and Pattern Recognition · Computer Science 2026-05-21 Hanxun Yu , Xuan Qu , Yuxin Wang , Jianke Zhu , Lei Ke