中文
相关论文

相关论文: RAZER: Robust Accelerated Zero-Shot 3D Open-Vocabu…

200 篇论文

Establishing dense correspondence across 3D shapes is crucial for fundamental downstream tasks, including texture transfer, shape interpolation, and robotic manipulation. However, learning these mappings without manual supervision remains a…

计算机视觉与模式识别 · 计算机科学 2026-03-10 Qinfeng Xiao , Guofeng Mei , Qilong Liu , Chenyuan Yi , Fabio Poiesi , Jian Zhang , Bo Yang , Yick Kit-lun

We propose an online 3D semantic segmentation method that incrementally reconstructs a 3D semantic map from a stream of RGB-D frames. Unlike offline methods, ours is directly applicable to scenarios with real-time constraints, such as…

计算机视觉与模式识别 · 计算机科学 2023-12-05 Silvan Weder , Francis Engelmann , Johannes L. Schönberger , Akihito Seki , Marc Pollefeys , Martin R. Oswald

Reconstructing and semantically interpreting 3D scenes from sparse 2D views remains a fundamental challenge in computer vision. Conventional methods often decouple semantic understanding from reconstruction or necessitate costly per-scene…

计算机视觉与模式识别 · 计算机科学 2026-03-25 Xiangyu Sun , Haoyi Jiang , Liu Liu , Seungtae Nam , Gyeongjin Kang , Xinjie Wang , Wei Sui , Zhizhong Su , Wenyu Liu , Xinggang Wang , Eunbyung Park

We introduce Dream2Real, a robotics framework which integrates vision-language models (VLMs) trained on 2D data into a 3D object rearrangement pipeline. This is achieved by the robot autonomously constructing a 3D representation of the…

机器人学 · 计算机科学 2024-07-31 Ivan Kapelyukh , Yifei Ren , Ignacio Alzugaray , Edward Johns

Building 3D maps of the environment is central to robot navigation, planning, and interaction with objects in a scene. Most existing approaches that integrate semantic concepts with 3D maps largely remain confined to the closed-set setting:…

Visual target navigation in unknown environments is a crucial problem in robotics. Despite extensive investigation of classical and learning-based approaches in the past, robots lack common-sense knowledge about household objects and…

机器人学 · 计算机科学 2023-12-27 Bangguo Yu , Hamidreza Kasaei , Ming Cao

3D scene understanding spans reasoning about free space, object grounding, hypothetical object insertions, complex geometric relationships, and integrating all of these with external tools and data sources. Existing 3D understanding methods…

计算机视觉与模式识别 · 计算机科学 2026-05-12 Sagar Bharadwaj , Ziyong Ma , Anurag Ghosh , Srinivasan Seshan , Anthony Rowe

Open-vocabulary 3D scene understanding (OV-3D) aims to localize and classify novel objects beyond the closed set of object classes. However, existing approaches and benchmarks primarily focus on the open vocabulary problem within the…

计算机视觉与模式识别 · 计算机科学 2025-11-26 Youjun Zhao , Jiaying Lin , Shuquan Ye , Qianshi Pang , Rynson W. H. Lau

Open vocabulary 3D object detection (OV3D) allows precise and extensible object recognition crucial for adapting to diverse environments encountered in assistive robotics. This paper presents OpenNav, a zero-shot 3D object detection…

计算机视觉与模式识别 · 计算机科学 2024-08-27 Muhammad Rameez ur Rahman , Piero Simonetto , Anna Polato , Francesco Pasti , Luca Tonin , Sebastiano Vascon

Performing single image holistic understanding and 3D reconstruction is a central task in computer vision. This paper presents an integrated system that performs dense scene labeling, object detection, instance segmentation, depth…

计算机视觉与模式识别 · 计算机科学 2021-12-01 Sainan Liu , Vincent Nguyen , Yuan Gao , Subarna Tripathi , Zhuowen Tu

We study open-world 3D scene understanding, a family of tasks that require agents to reason about their 3D environment with an open-set vocabulary and out-of-domain visual inputs - a critical skill for robots to operate in the unstructured…

计算机视觉与模式识别 · 计算机科学 2022-12-07 Huy Ha , Shuran Song

Understanding the geometric and semantic structure of environments is essential for embodied navigation and reasoning. Existing semantic mapping methods trade off between explicit geometry and multi-scale semantics, and lack a native…

计算机视觉与模式识别 · 计算机科学 2026-05-05 Sixian Zhang , Yiyao Wang , Xinhang Song , Keming Zhang , Zijian Xu , Shuqiang Jiang

We investigate transductive zero-shot point cloud semantic segmentation, where the network is trained on seen objects and able to segment unseen objects. The 3D geometric elements are essential cues to imply a novel 3D object type. However,…

计算机视觉与模式识别 · 计算机科学 2023-10-02 Runnan Chen , Xinge Zhu , Nenglun Chen , Wei Li , Yuexin Ma , Ruigang Yang , Wenping Wang

Seamless integration of virtual and physical worlds in augmented reality benefits from the system semantically "understanding" the physical environment. AR research has long focused on the potential of context awareness, demonstrating novel…

人机交互 · 计算机科学 2024-10-08 Chengyuan Xu , Radha Kumaran , Noah Stier , Kangyou Yu , Tobias Höllerer

With the explosive 3D data growth, the urgency of utilizing zero-shot learning to facilitate data labeling becomes evident. Recently, methods transferring language or language-image pre-training models like Contrastive Language-Image…

计算机视觉与模式识别 · 计算机科学 2024-04-17 Weiguang Zhao , Guanyu Yang , Rui Zhang , Chenru Jiang , Chaolong Yang , Yuyao Yan , Amir Hussain , Kaizhu Huang

Neural rendering has demonstrated remarkable success in high-quality 3D neural reconstruction and novel view synthesis with dense input views and accurate poses. However, applying it to extremely sparse, unposed views in unbounded 360{\deg}…

计算机视觉与模式识别 · 计算机科学 2025-04-01 Chong Bao , Xiyu Zhang , Zehao Yu , Jiale Shi , Guofeng Zhang , Songyou Peng , Zhaopeng Cui

Self-supervised pre-training has driven rapid progress in foundation models for language, 2D images, and video, yet remains largely unexplored for learning 3D-aware representations from multi-view images. In this paper, we present E-RayZer,…

计算机视觉与模式识别 · 计算机科学 2026-03-31 Qitao Zhao , Hao Tan , Qianqian Wang , Sai Bi , Kai Zhang , Kalyan Sunkavalli , Shubham Tulsiani , Hanwen Jiang

Open-vocabulary panoptic reconstruction is a challenging task for simultaneous scene reconstruction and understanding. Recently, methods have been proposed for 3D scene understanding based on Gaussian splatting. However, these methods are…

计算机视觉与模式识别 · 计算机科学 2025-03-25 Yuxuan Xie , Xuan Yu , Changjian Jiang , Sitong Mao , Shunbo Zhou , Rui Fan , Rong Xiong , Yue Wang

Zero-shot 3D Visual Grounding (3DVG) is a critical capability for open-world embodied AI. However, existing methods are fundamentally bottlenecked by the poor quality of open-vocabulary 3D proposals, suffering from inaccurate categories and…

计算机视觉与模式识别 · 计算机科学 2026-04-30 Yufei Yin , Jie Zheng , Qianke Meng , Zhou Yu , Minghao Chen , Jiajun Ding , Min Tan , Yuling Xi , Zhiwen Chen , Chengfei Lv

This paper presents VGGT-360, a novel training-free framework for zero-shot, geometry-consistent panoramic depth estimation. Unlike prior view-independent training-free approaches, VGGT-360 reformulates the task as panoramic reprojection…

计算机视觉与模式识别 · 计算机科学 2026-05-15 Jiayi Yuan , Haobo Jiang , De Wen Soh , Na Zhao