English
Related papers

Related papers: Kestrel: 3D Multimodal LLM for Part-Aware Grounded…

200 papers

3D object grounding localizes referred objects in a 3D scene from natural language. Unified instance-centric 3D-LLMs aim to solve grounding together with dialog, QA, and captioning, yet many rely on a single pointer-style grounding decision…

Computer Vision and Pattern Recognition · Computer Science 2026-05-28 Jiawei Li , Ziyi Liu , Weijie Shi , Long Chen , Jiajie Xu , Xiaofang Zhou

Existing open-vocabulary 3D semantic segmentation methods typically supervise 3D segmentation models by merging text-aligned features (e.g., CLIP) extracted from multi-view images onto 3D points. However, such approaches treat multi-view…

Computer Vision and Pattern Recognition · Computer Science 2025-07-01 Shiqi Zhang , Sha Zhang , Jiajun Deng , Yedong Shen , Mingxiao MA , Yanyong Zhang

3D visual grounding aims to automatically locate the 3D region of the specified object given the corresponding textual description. Existing works fail to distinguish similar objects especially when multiple referred objects are involved in…

Computer Vision and Pattern Recognition · Computer Science 2024-03-14 Feng Xiao , Hongbin Xu , Qiuxia Wu , Wenxiong Kang

The promotion of construction robots can solve the problem of human resource shortage and improve the quality of decoration. To help the construction robots obtain environmental information, we need to use 3D point cloud, which is widely…

Robotics · Computer Science 2021-04-13 Xudong Li , Li Feng , Lei Li , Chen Wang

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

We introduce Part-X-MLLM, a native 3D multimodal large language model that unifies diverse 3D tasks by formulating them as programs in a structured, executable grammar. Given an RGB point cloud and a natural language prompt, our model…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Chunshi Wang , Junliang Ye , Yunhan Yang , Yang Li , Zizhuo Lin , Jun Zhu , Zhuo Chen , Yawei Luo , Chunchao Guo

Accurate 3D scene representation and panoptic understanding are essential for applications such as virtual reality, robotics, and autonomous driving. However, challenges persist with existing methods, including precise 2D-to-3D mapping,…

Computer Vision and Pattern Recognition · Computer Science 2024-10-08 Shenghao Li

Recent advances in data-driven models for grounded language understanding have enabled robots to interpret increasingly complex instructions. Two fundamental limitations of these methods are that most require a full model of the environment…

Robotics · Computer Science 2019-10-23 Siddharth Patki , Ethan Fahnestock , Thomas M. Howard , Matthew R. Walter

Recent advances in large vision-language models (VLMs) have shown significant promise for 3D scene understanding. Existing VLM-based approaches typically align 3D scene features with the VLM's embedding space. However, this implicit…

Computer Vision and Pattern Recognition · Computer Science 2025-12-01 Chen Li , Eric Peh , Basura Fernando

Reasoning segmentation has recently expanded from ground-level scenes to remote-sensing imagery, yet UAV data poses distinct challenges, including oblique viewpoints, ultra-high resolutions, and extreme scale variations. To address these…

Computer Vision and Pattern Recognition · Computer Science 2026-04-20 Shuyan Ke , Yifan Mei , Changli Wu , Yonghan Zheng , Jiayi Ji , Liujuan Cao , Rongrong Ji

Visual grounding aims to identify objects or regions in a scene based on natural language descriptions, essential for spatially aware perception in autonomous driving. However, existing visual grounding tasks typically depend on bounding…

Computer Vision and Pattern Recognition · Computer Science 2025-09-04 Zhan Shi , Song Wang , Junbo Chen , Jianke Zhu

Recent advancements in Multimodal Large Language Models (MLLMs) have greatly improved their abilities in image understanding. However, these models often struggle with grasping pixel-level semantic details, e.g., the keypoints of an object.…

Computer Vision and Pattern Recognition · Computer Science 2024-11-05 Jie Yang , Wang Zeng , Sheng Jin , Lumin Xu , Wentao Liu , Chen Qian , Ruimao Zhang

3D part segmentation is a crucial and challenging task in 3D perception, playing a vital role in applications such as robotics, 3D generation, and 3D editing. Recent methods harness the powerful Vision Language Models (VLMs) for 2D-to-3D…

Computer Vision and Pattern Recognition · Computer Science 2024-11-19 Yunhan Yang , Yukun Huang , Yuan-Chen Guo , Liangjun Lu , Xiaoyang Wu , Edmund Y. Lam , Yan-Pei Cao , Xihui Liu

The rapid progress of Multimodal Large Language Models (MLLMs) has unlocked the potential for enhanced 3D scene understanding and spatial reasoning. A recent line of work explores learning spatial reasoning directly from multi-view images,…

Computer Vision and Pattern Recognition · Computer Science 2026-04-10 Kanghee Lee , Injae Lee , Minseok Kwak , Jungi Hong , Kwonyoung Ryu , Jaesik Park

3D visual grounding (3DVG) involves localizing entities in a 3D scene referred to by natural language text. Such models are useful for embodied AI and scene retrieval applications, which involve searching for objects or patterns using…

Computer Vision and Pattern Recognition · Computer Science 2025-07-09 Austin T. Wang , ZeMing Gong , Angel X. Chang

Most multimodal large language models (MLLMs) learn language-to-object grounding through causal language modeling where grounded objects are captured by bounding boxes as sequences of location tokens. This paradigm lacks pixel-level…

Computer Vision and Pattern Recognition · Computer Science 2024-04-17 Yichi Zhang , Ziqiao Ma , Xiaofeng Gao , Suhaila Shakiah , Qiaozi Gao , Joyce Chai

We propose a lightweight and scalable Regional Point-Language Contrastive learning framework, namely \textbf{RegionPLC}, for open-world 3D scene understanding, aiming to identify and recognize open-set objects and categories. Specifically,…

Computer Vision and Pattern Recognition · Computer Science 2024-05-07 Jihan Yang , Runyu Ding , Weipeng Deng , Zhe Wang , Xiaojuan Qi

Within a perception framework for autonomous mobile and robotic systems, semantic analysis of 3D point clouds typically generated by LiDARs is key to numerous applications, such as object detection and recognition, and scene reconstruction.…

Robotics · Computer Science 2024-10-14 Samir Abou Haidar , Alexandre Chariot , Mehdi Darouich , Cyril Joly , Jean-Emmanuel Deschaud

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

Recent advances in point cloud perception have demonstrated remarkable progress in scene understanding through vision-language alignment leveraging large language models (LLMs). However, existing methods may still encounter challenges in…

Computer Vision and Pattern Recognition · Computer Science 2025-07-01 Zhenhua Ning , Zhuotao Tian , Shaoshuai Shi , Guangming Lu , Daojing He , Wenjie Pei , Li Jiang