English
Related papers

Related papers: RAZER: Robust Accelerated Zero-Shot 3D Open-Vocabu…

200 papers

We present Ov3R, a novel framework for open-vocabulary semantic 3D reconstruction from RGB video streams, designed to advance Spatial AI. The system features two key components: CLIP3R, a CLIP-informed 3D reconstruction module that predicts…

Computer Vision and Pattern Recognition · Computer Science 2025-12-03 Ziren Gong , Xiaohan Li , Fabio Tosi , Jiawei Han , Stefano Mattoccia , Jianfei Cai , Matteo Poggi

Humans exhibit an innate capacity to rapidly perceive and segment objects from video observations, and even mentally assemble them into structured 3D scenes. Replicating such capability, termed compositional 3D reconstruction, is pivotal…

Computer Vision and Pattern Recognition · Computer Science 2026-04-14 Mingyu Dong , Chong Xia , Mingyuan Jia , Weichen Lyu , Long Xu , Zheng Zhu , Yueqi Duan

Recent advancements in open-vocabulary 3D scene understanding heavily rely on 3D Gaussian Splatting (3DGS) to register vision-language features into 3D space. However, we identify two critical limitations in these approaches: the spatial…

Computer Vision and Pattern Recognition · Computer Science 2026-04-03 Fusang Wang , Nathan Piasco , Moussab Bennehar , Luis Roldão , Dzmitry Tsishkou , Fabien Moutarde

The integration of geometric reconstruction and generative modeling remains a critical challenge in developing AI systems capable of human-like spatial reasoning. This paper proposes Aether, a unified framework that enables geometry-aware…

Computer Vision and Pattern Recognition · Computer Science 2025-07-29 Aether Team , Haoyi Zhu , Yifan Wang , Jianjun Zhou , Wenzheng Chang , Yang Zhou , Zizun Li , Junyi Chen , Chunhua Shen , Jiangmiao Pang , Tong He

In this paper, we rethink the problem of scene reconstruction from an embodied agent's perspective: While the classic view focuses on the reconstruction accuracy, our new perspective emphasizes the underlying functions and constraints such…

Robotics · Computer Science 2021-03-31 Muzhi Han , Zeyu Zhang , Ziyuan Jiao , Xu Xie , Yixin Zhu , Song-Chun Zhu , Hangxin Liu

Understanding open-vocabulary 3D scenes with Gaussian-based representations remains challenging due to fragmented and spatially inconsistent semantic predictions across multi-view observations. In this paper, we present OpenGaFF, a novel…

Computer Vision and Pattern Recognition · Computer Science 2026-05-25 Kunyi Li , Michael Niemeyer , Sen Wang , Stefano Gasperini , Nassir Navab , Federico Tombari

Open-vocabulary scene understanding with online panoptic mapping is essential for embodied applications to perceive and interact with environments. However, existing methods are predominantly offline or lack instance-level understanding,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-20 Hongjia Zhai , Qi Zhang , Xiaokun Pan , Xiyu Zhang , Yitong Dong , Huaqi Zhang , Dan Xu , Guofeng Zhang

We propose OpenVoxel, a training-free algorithm for grouping and captioning sparse voxels for the open-vocabulary 3D scene understanding tasks. Given the sparse voxel rasterization (SVR) model obtained from multi-view images of a 3D scene,…

Computer Vision and Pattern Recognition · Computer Science 2026-01-15 Sheng-Yu Huang , Jaesung Choe , Yu-Chiang Frank Wang , Cheng Sun

3D Visual Grounding (3DVG) aims at localizing 3D object based on textual descriptions. Conventional supervised methods for 3DVG often necessitate extensive annotations and a predefined vocabulary, which can be restrictive. To address this…

Computer Vision and Pattern Recognition · Computer Science 2024-03-26 Zhihao Yuan , Jinke Ren , Chun-Mei Feng , Hengshuang Zhao , Shuguang Cui , Zhen Li

This work presents OVIR-3D, a straightforward yet effective method for open-vocabulary 3D object instance retrieval without using any 3D data for training. Given a language query, the proposed method is able to return a ranked set of 3D…

Computer Vision and Pattern Recognition · Computer Science 2023-11-07 Shiyang Lu , Haonan Chang , Eric Pu Jing , Abdeslam Boularias , Kostas Bekris

Semantic 3D scene understanding is a problem of critical importance in robotics. While significant advances have been made in simultaneous localization and mapping algorithms, robots are still far from having the common sense knowledge…

Robotics · Computer Science 2022-06-22 William Chen , Siyi Hu , Rajat Talak , Luca Carlone

We introduce the task of open-vocabulary 3D instance segmentation. Current approaches for 3D instance segmentation can typically only recognize object categories from a pre-defined closed set of classes that are annotated in the training…

Computer Vision and Pattern Recognition · Computer Science 2023-10-31 Ayça Takmaz , Elisabetta Fedele , Robert W. Sumner , Marc Pollefeys , Federico Tombari , Francis Engelmann

Open-vocabulary 3D visual grounding aims to localize target objects based on free-form language queries, which is crucial for embodied AI applications such as autonomous navigation, robotics, and augmented reality. Learning 3D language…

Computer Vision and Pattern Recognition · Computer Science 2025-07-10 Zhenyang Liu , Sixiao Zheng , Siyu Chen , Cairong Zhao , Longfei Liang , Xiangyang Xue , Yanwei Fu

Abstract semantic 3D scene understanding is a problem of critical importance in robotics. As robots still lack the common-sense knowledge about household objects and locations of an average human, we investigate the use of pre-trained…

Robotics · Computer Science 2023-11-09 William Chen , Siyi Hu , Rajat Talak , Luca Carlone

Robotic grasping is a cornerstone capability of embodied systems. Many methods directly output grasps from partial information without modeling the geometry of the scene, leading to suboptimal motion and even collisions. To address these…

Recent advancements in 3D reconstruction methods and vision-language models have propelled the development of multi-modal 3D scene understanding, which has vital applications in robotics, autonomous driving, and virtual/augmented reality.…

Computer Vision and Pattern Recognition · Computer Science 2025-05-06 Qucheng Peng , Benjamin Planche , Zhongpai Gao , Meng Zheng , Anwesa Choudhuri , Terrence Chen , Chen Chen , Ziyan Wu

Open-vocabulary 3D object detection (OV-3DDet) aims to localize and recognize both seen and previously unseen object categories within any new 3D scene. While language and vision foundation models have achieved success in handling various…

Computer Vision and Pattern Recognition · Computer Science 2024-07-18 Pengkun Jiao , Na Zhao , Jingjing Chen , Yu-Gang Jiang

3D Gaussian Splatting offers expressive scene reconstruction, modeling a broad range of visual, geometric, and semantic information. However, efficient real-time map reconstruction with data streamed from multiple robots and devices remains…

Robotics · Computer Science 2025-06-04 Javier Yu , Timothy Chen , Mac Schwager

Functional 3D scene graphs offer a versatile and flexible representation for 3D scene understanding and robotic manipulation, defined by object nodes, interactive elements, and functional relationship edges. However, their potential remains…

The acquisition of large-scale physical interaction data, a critical prerequisite for modern robot learning, is severely bottlenecked by the prohibitive cost and scalability limits of human-in-the-loop collection paradigms. To break this…

Robotics · Computer Science 2026-03-13 Yongzhong Wang , Keyu Zhu , Yong Zhong , Liqiong Wang , Jinyu Yang , Feng Zheng