English
Related papers

Related papers: PanoGrounder: Bridging 2D and 3D with Panoramic Sc…

200 papers

Vision-language models (VLMs) are essential to Embodied AI, enabling robots to perceive, reason, and act in complex environments. They also serve as the foundation for the recent Vision-Language-Action (VLA) models. Yet most evaluations of…

Indoor scene understanding remains a fundamental challenge in robotics, with direct implications for downstream tasks such as navigation and manipulation. Traditional approaches often rely on closed-set recognition or loop closure, limiting…

Robotics · Computer Science 2025-06-10 Hongming Chen , Yiyang Lin , Ziliang Li , Biyu Ye , Yuying Zhang , Ximin Lyu

Vision-language models (VLMs) have advanced multimodal reasoning but still face challenges in spatial reasoning for 3D scenes and complex object configurations. To address this, we introduce SpatialViLT, an enhanced VLM that integrates…

Computer Vision and Pattern Recognition · Computer Science 2025-10-07 Chashi Mahiul Islam , Oteo Mamo , Samuel Jacob Chacko , Xiuwen Liu , Weikuan Yu

Multimodal large language models have demonstrated remarkable capabilities in 2D vision, motivating their extension to 3D scene understanding. Recent studies represent 3D scenes as 3D spatial videos composed of image sequences with depth…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Han Li , Zehao Huang , Jiahui Fu , Naiyan Wang , Si Liu

Representing and understanding 3D environments in a structured manner is crucial for autonomous agents to navigate and reason about their surroundings. While traditional Simultaneous Localization and Mapping (SLAM) methods generate metric…

Robotics · Computer Science 2026-02-03 Albert Gassol Puigjaner , Angelos Zacharia , Kostas Alexis

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

Open-vocabulary panoptic reconstruction is essential for advanced robotics perception and simulation. However, existing methods based on 3D Gaussian Splatting (3DGS) often struggle to simultaneously achieve geometric accuracy, coherent…

Robotics · Computer Science 2026-04-14 Xuan Yu , Yuxuan Xie , Changjian Jiang , Shichao Zhai , Rong Xiong , Yu Zhang , Yue Wang

Large Vision-Language Models (LVLMs) offer remarkable benefits for a variety of vision-language tasks. However, a challenge hindering their application in real-world scenarios, particularly regarding safety, robustness, and reliability, is…

Computer Vision and Pattern Recognition · Computer Science 2024-01-17 Jiaying Lu , Jinmeng Rao , Kezhen Chen , Xiaoyuan Guo , Yawen Zhang , Baochen Sun , Carl Yang , Jie Yang

Vision-language models (VLMs) have demonstrated strong performance in 2D scene understanding and generation, but extending this unification to the physical world remains an open challenge. Existing 3D and 4D approaches typically embed scene…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Hanyu Zhou , Gim Hee Lee

Robots are finding wider adoption in human environments, increasing the need for natural human-robot interaction. However, understanding a natural language command requires the robot to infer the intended task and how to decompose it into…

Robotics · Computer Science 2026-02-05 Julia Kuhn , Francesco Verdoja , Tsvetomila Mihaylova , Ville Kyrki

Geometry estimation from perspective images has greatly advanced, maturing to the point where off-the-shelf foundation models are able to reconstruct 3D scene structure not only from multi-view imagery, but even from a single view. A…

Computer Vision and Pattern Recognition · Computer Science 2026-05-28 Vukasin Bozic , Isidora Slavkovic , Dominik Narnhofer , Nando Metzger , Denis Rozumny , Konrad Schindler , Nikolai Kalischek

3D vision-language grounding, which focuses on aligning language with the 3D physical environment, stands as a cornerstone in the development of embodied agents. In comparison to recent advancements in the 2D domain, grounding language in…

Computer Vision and Pattern Recognition · Computer Science 2024-09-25 Baoxiong Jia , Yixin Chen , Huangyue Yu , Yan Wang , Xuesong Niu , Tengyu Liu , Qing Li , Siyuan Huang

Visual grounding, localizing objects from natural language descriptions, represents a critical bridge between language and vision understanding. While multimodal large language models (MLLMs) achieve impressive scores on existing…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Rang Li , Lei Li , Shuhuai Ren , Hao Tian , Shuhao Gu , Shicheng Li , Zihao Yue , Yudong Wang , Wenhan Ma , Zhe Yang , Jingyuan Ma , Zhifang Sui , Fuli Luo

Precise spatial reasoning is fundamental to robotic manipulation, yet the visual backbones of current vision-language-action (VLA) models are predominantly pretrained on 2D image data without explicit 3D geometric supervision, resulting in…

Fine-grained alignment between videos and text is challenging due to complex spatial and temporal dynamics in videos. Existing video-based Large Multimodal Models (LMMs) handle basic conversations but struggle with precise pixel-level…

Computer Vision and Pattern Recognition · Computer Science 2025-03-26 Shehan Munasinghe , Hanan Gani , Wenqi Zhu , Jiale Cao , Eric Xing , Fahad Shahbaz Khan , Salman Khan

Large vision-language models (VLMs) have made significant strides in 2D visual understanding tasks, sparking interest in extending these capabilities to 3D scene understanding. However, current 3D VLMs often struggle with robust reasoning…

Computer Vision and Pattern Recognition · Computer Science 2025-08-01 Ting Huang , Zeyu Zhang , Hao Tang

Spatial intelligence requires visual representations that capture both semantic objects and geometric structure in the physical world. To support this, two major pre-training schemes are now widely used as foundation backbones:…

Computer Vision and Pattern Recognition · Computer Science 2026-05-28 Haozhan Shen , Tiancheng Zhao , Kangjia Zhao , Jianwei Yin

Existing Vision Language Models (VLMs) architecturally rooted in "flatland" perception, fundamentally struggle to comprehend real-world 3D spatial intelligence. This failure stems from a dual-bottleneck: input-stage conflict between…

Computer Vision and Pattern Recognition · Computer Science 2025-11-19 Zhongbin Guo , Jiahe Liu , Yushan Li , Wenyu Gao , Zhen Yang , Chenzhi Li , Xinyue Zhang , Ping Jian

Current large vision-language models (LVLMs) typically employ a connector module to link visual features with text embeddings of large language models (LLMs) and use end-to-end training to achieve multi-modal understanding in a unified…

Artificial Intelligence · Computer Science 2025-08-14 Zixian Guo , Ming Liu , Qilong Wang , Zhilong Ji , Jinfeng Bai , Lei Zhang , Wangmeng Zuo

Natural language applied to natural 2D images describes a fundamentally 3D world. We present the Voxel-informed Language Grounder (VLG), a language grounding model that leverages 3D geometric information in the form of voxel maps derived…

Computation and Language · Computer Science 2022-05-20 Rodolfo Corona , Shizhan Zhu , Dan Klein , Trevor Darrell