中文
相关论文

相关论文: AI's Spatial Intelligence: Evaluating AI's Underst…

200 篇论文

In this paper, we introduce SPA, a novel representation learning framework that emphasizes the importance of 3D spatial awareness in embodied AI. Our approach leverages differentiable neural rendering on multi-view images to endow a vanilla…

计算机视觉与模式识别 · 计算机科学 2025-03-04 Haoyi Zhu , Honghui Yang , Yating Wang , Jiange Yang , Limin Wang , Tong He

Embodied scene understanding requires not only comprehending visual-spatial information that has been observed but also determining where to explore next in the 3D physical world. Existing 3D Vision-Language (3D-VL) models primarily focus…

计算机视觉与模式识别 · 计算机科学 2025-07-31 Ziyu Zhu , Xilin Wang , Yixuan Li , Zhuofan Zhang , Xiaojian Ma , Yixin Chen , Baoxiong Jia , Wei Liang , Qian Yu , Zhidong Deng , Siyuan Huang , Qing Li

Achieving human-like spatial intelligence for vision-language models (VLMs) requires inferring 3D structures from 2D observations, recognizing object properties and relations in 3D space, and performing high-level spatial reasoning. In this…

计算机视觉与模式识别 · 计算机科学 2026-03-27 Huizhi Liang , Yichao Shen , Yu Deng , Sicheng Xu , Zhiyuan Feng , Tong Zhang , Yaobo Liang , Jiaolong Yang

The ability to jointly understand the geometry of objects and plan actions for manipulating them is crucial for intelligent agents. We refer to this ability as geometric planning. Recently, many interactive environments have been proposed…

机器学习 · 计算机科学 2020-07-23 Ankit Goyal , Jia Deng

Artificial Intelligence significantly enhances the visual art industry by analyzing, identifying and generating digitized artistic images. This review highlights the substantial benefits of integrating geometric data into AI models,…

人工智能 · 计算机科学 2024-12-03 Mridula Vijendran , Jingjing Deng , Shuang Chen , Edmond S. L. Ho , Hubert P. H. Shum

Recent unified image generation models have achieved remarkable success by employing MLLMs for semantic understanding and diffusion backbones for image generation. However, these models remain fundamentally limited in spatially-aware tasks…

计算机视觉与模式识别 · 计算机科学 2026-04-30 Haiyi Qiu , Kaihang Pan , Jiacheng Li , Juncheng Li , Siliang Tang , Yueting Zhuang

Existing RGB-based imitation learning approaches typically employ traditional vision encoders such as ResNet or ViT, which lack explicit 3D reasoning capabilities. Recent geometry-grounded vision models, such as VGGT~\cite{wang2025vggt},…

机器人学 · 计算机科学 2025-09-22 An Dinh Vuong , Minh Nhat Vu , Ian Reid

How to integrate and verify spatial intelligence in foundation models remains an open challenge. Current practice often proxies Visual-Spatial Intelligence (VSI) with purely textual prompts and VQA-style scoring, which obscures geometry,…

计算机视觉与模式识别 · 计算机科学 2025-10-27 Guanlin Wu , Boyan Su , Yang Zhao , Pu Wang , Yichen Lin , Hao Frank Yang

Existing self-supervised learning (SSL) methods primarily learn object-invariant representations but often neglect the spatial structure and relationships among object parts. To address this limitation, we introduce Spatial Prediction (SP),…

计算机视觉与模式识别 · 计算机科学 2026-05-12 Yang Shen , Yusen Cai , Weronika Hryniewska-Guzik , Qing Lin , Mengmi Zhang

Current state-of-the-art spatial reasoning-enhanced VLMs are trained to excel at spatial visual question answering (VQA). However, we believe that higher-level 3D-aware tasks, such as articulating dynamic scene changes and motion planning,…

计算机视觉与模式识别 · 计算机科学 2024-10-31 Chenyang Ma , Kai Lu , Ta-Ying Cheng , Niki Trigoni , Andrew Markham

We discuss and predict the evolution of Simultaneous Localisation and Mapping (SLAM) into a general geometric and semantic `Spatial AI' perception capability for intelligent embodied devices. A big gap remains between the visual perception…

人工智能 · 计算机科学 2018-04-02 Andrew J. Davison

The Theory of Multiple Intelligences underscores the hierarchical nature of cognitive capabilities. To advance Spatial Artificial Intelligence, we pioneer a psychometric framework defining five Basic Spatial Abilities (BSAs) in Visual…

计算机视觉与模式识别 · 计算机科学 2025-08-06 Wenrui Xu , Dalin Lyu , Weihang Wang , Jie Feng , Chen Gao , Yong Li

Rapid developments in advanced sensing and imaging have significantly enhanced information visibility, opening opportunities for predictive modeling of complex dynamic systems. However, sensing signals acquired from such complex systems are…

机器学习 · 统计学 2025-05-02 Xizhuo Zhang , Bing Yao

Large language models (LLMs) have undergone significant expansion and have been increasingly integrated across various domains. Notably, in the realm of robot task planning, LLMs harness their advanced reasoning and language comprehension…

Service robots are expected to reliably make sense of complex, fast-changing environments. From a cognitive standpoint, they need the appropriate reasoning capabilities and background knowledge required to exhibit human-like Visual…

人工智能 · 计算机科学 2021-04-02 Agnese Chiatti , Gianluca Bardaro , Enrico Motta , Enrico Daga

Current evaluations of spatial intelligence can be systematically invalid under modern vision-language model (VLM) settings. First, many benchmarks derive question-answer (QA) pairs from point-cloud-based 3D annotations originally curated…

计算机视觉与模式识别 · 计算机科学 2026-05-07 Yiming Zhang , Jiacheng Chen , Jiaqi Tan , Yongsen Mao , Wenhu Chen , Angel X. Chang

Human-centered environments are rich with a wide variety of spatial relations between everyday objects. For autonomous robots to operate effectively in such environments, they should be able to reason about these relations and generalize…

机器人学 · 计算机科学 2017-07-25 Oier Mees , Nichola Abdo , Mladen Mazuran , Wolfram Burgard

Visual Place Recognition (VPR) is often characterized as being able to recognize the same place despite significant changes in appearance and viewpoint. VPR is a key component of Spatial Artificial Intelligence, enabling robotic platforms…

机器人学 · 计算机科学 2021-11-10 Sourav Garg , Tobias Fischer , Michael Milford

Spatial understanding is a fundamental problem with wide-reaching real-world applications. The representation of spatial knowledge is often modeled with spatial templates, i.e., regions of acceptability of two objects under an explicit…

人工智能 · 计算机科学 2020-03-09 Guillem Collell , Luc Van Gool , Marie-Francine Moens

Robot vision has greatly benefited from advancements in multimodal fusion techniques and vision-language models (VLMs). We adopt a task-oriented perspective to systematically review the applications and advancements of multimodal fusion…

‹ 上一页 1 8 9 10 下一页 ›