English
Related papers

Related papers: InstanceRefer: Cooperative Holistic Understanding …

200 papers

Localizing objects in 3D scenes based on natural language requires understanding and reasoning about spatial relations. In particular, it is often crucial to distinguish similar objects referred by the text, such as "the left most chair"…

Computer Vision and Pattern Recognition · Computer Science 2022-11-18 Shizhe Chen , Pierre-Louis Guhur , Makarand Tapaswi , Cordelia Schmid , Ivan Laptev

3D visual grounding (VG) aims to locate objects or regions within 3D scenes guided by natural language descriptions. While indoor 3D VG has advanced, outdoor 3D VG remains underexplored due to two challenges: (1) large-scale outdoor LiDAR…

Computer Vision and Pattern Recognition · Computer Science 2025-08-01 Yeong-Seung Baek , Heung-Seon Oh

3D visual grounding is the task of localizing the object in a 3D scene which is referred by a description in natural language. With a wide range of applications ranging from autonomous indoor robotics to AR/VR, the task has recently risen…

Computer Vision and Pattern Recognition · Computer Science 2024-07-17 Ozan Unal , Christos Sakaridis , Suman Saha , Luc Van Gool

3D visual grounding is the ability to localize objects in 3D scenes conditioned by utterances. Most existing methods devote the referring head to localize the referred object directly, causing failure in complex scenarios. In addition, it…

Computer Vision and Pattern Recognition · Computer Science 2024-10-08 Eslam Abdelrahman , Mohamed Ayman , Mahmoud Ahmed , Habib Slim , Mohamed Elhoseiny

Generalized visual grounding tasks, including Generalized Referring Expression Comprehension (GREC) and Segmentation (GRES), extend the classical visual grounding paradigm by accommodating multi-target and non-target scenarios.…

Computer Vision and Pattern Recognition · Computer Science 2025-09-18 Ming Dai , Wenxuan Cheng , Jiang-Jiang Liu , Lingfeng Yang , Zhenhua Feng , Wankou Yang , Jingdong Wang

Most models tasked to ground referential utterances in 2D and 3D scenes learn to select the referred object from a pool of object proposals provided by a pre-trained detector. This is limiting because an utterance may refer to visual…

Computer Vision and Pattern Recognition · Computer Science 2022-07-22 Ayush Jain , Nikolaos Gkanatsios , Ishita Mediratta , Katerina Fragkiadaki

3D instance segmentation aims to predict a set of object instances in a scene, representing them as binary foreground masks with corresponding semantic labels. Currently, transformer-based methods are gaining increasing attention due to…

Computer Vision and Pattern Recognition · Computer Science 2025-06-24 Jiahao Lu , Jiacheng Deng

Generalised 3D Referring Expression Segmentation (3D-GRES) localizes objects in 3D scenes based on natural language, even when descriptions match multiple or zero targets. Existing methods rely solely on sparse point clouds, lacking rich…

Computer Vision and Pattern Recognition · Computer Science 2026-03-09 Keshen Zhou , Runnan Chen , Mingming Gong , Tongliang Liu

This paper addresses the problem of 3D referring expression comprehension (REC) in autonomous driving scenario, which aims to ground a natural language to the targeted region in LiDAR point clouds. Previous approaches for REC usually focus…

Computer Vision and Pattern Recognition · Computer Science 2023-05-26 Wenhao Cheng , Junbo Yin , Wei Li , Ruigang Yang , Jianbing Shen

Recognizing 3D part instances from a 3D point cloud is crucial for 3D structure and scene understanding. Several learning-based approaches use semantic segmentation and instance center prediction as training tasks and fail to further…

Computer Vision and Pattern Recognition · Computer Science 2022-08-10 Chunyu Sun , Xin Tong , Yang Liu

Text-to-point-cloud cross-modal localization is an emerging vision-language task critical for future robot-human collaboration. It seeks to localize a position from a city-scale point cloud scene based on a few natural language…

Computer Vision and Pattern Recognition · Computer Science 2024-04-30 Lichao Wang , Zhihao Yuan , Jinke Ren , Shuguang Cui , Zhen Li

3D Visual Grounding (3DVG) aims to localize the referent of natural language referring expressions through two core tasks: Referring Expression Comprehension (3DREC) and Segmentation (3DRES). While existing methods achieve high accuracy in…

Computer Vision and Pattern Recognition · Computer Science 2026-03-19 Wenbin Tan , Jiawen Lin , Fangyong Wang , Yuan Xie , Yong Xie , Yachao Zhang , Yanyun Qu

We introduce the novel task of Language-Guided Object Placement in Real 3D Scenes. Our model is given a 3D scene's point cloud, a 3D asset, and a textual prompt broadly describing where the 3D asset should be placed. The task here is to…

Computer Vision and Pattern Recognition · Computer Science 2025-10-03 Ahmed Abdelreheem , Filippo Aleotti , Jamie Watson , Zawar Qureshi , Abdelrahman Eldesokey , Peter Wonka , Gabriel Brostow , Sara Vicente , Guillermo Garcia-Hernando

This paper tackles the challenging task of 3D visual grounding-locating a specific object in a 3D point cloud scene based on text descriptions. Existing methods fall into two categories: top-down and bottom-up methods. Top-down methods rely…

Computer Vision and Pattern Recognition · Computer Science 2024-10-22 Yang Liu , Daizong Liu , Wei Hu

Recent deep learning models achieve impressive results on 3D scene analysis tasks by operating directly on unstructured point clouds. A lot of progress was made in the field of object classification and semantic segmentation. However, the…

Computer Vision and Pattern Recognition · Computer Science 2019-12-20 Cathrin Elich , Francis Engelmann , Theodora Kontogianni , Bastian Leibe

Modern 3D semantic instance segmentation approaches predominantly rely on specialized voting mechanisms followed by carefully designed geometric clustering techniques. Building on the successes of recent Transformer-based methods for object…

Computer Vision and Pattern Recognition · Computer Science 2023-04-13 Jonas Schult , Francis Engelmann , Alexander Hermans , Or Litany , Siyu Tang , Bastian Leibe

3D object grounding aims to locate the most relevant target object in a raw point cloud scene based on a free-form language description. Understanding complex and diverse descriptions, and lifting them directly to a point cloud is a new and…

Computer Vision and Pattern Recognition · Computer Science 2021-03-31 Mingtao Feng , Zhen Li , Qi Li , Liang Zhang , XiangDong Zhang , Guangming Zhu , Hui Zhang , Yaonan Wang , Ajmal Mian

Most recent 3D instance segmentation methods are open vocabulary, offering a greater flexibility than closed-vocabulary methods. Yet, they are limited to reasoning within a specific set of concepts, \ie the vocabulary, prompted by the user…

Computer Vision and Pattern Recognition · Computer Science 2025-03-31 Guofeng Mei , Luigi Riz , Yiming Wang , Fabio Poiesi

Multi-instance point cloud registration estimates the poses of multiple instances of a model point cloud in a scene point cloud. Extracting accurate point correspondence is to the center of the problem. Existing approaches usually treat the…

Computer Vision and Pattern Recognition · Computer Science 2024-04-09 Zhiyuan Yu , Zheng Qin , Lintao Zheng , Kai Xu

Real-time 3D object detection from point clouds is essential for dynamic scene understanding in applications such as augmented reality, robotics and navigation. We introduce a novel Spatial-prioritized and Rank-aware 3D object detection…

Computer Vision and Pattern Recognition · Computer Science 2025-11-21 Chenyu Zhao , Xianwei Zheng , Zimin Xia , Linwei Yue , Nan Xue