中文
相关论文

相关论文: PGOV3D: Open-Vocabulary 3D Semantic Segmentation w…

200 篇论文

3D scene understanding is fundamental for embodied AI and robotics, supporting reliable perception for interaction and navigation. Recent approaches achieve zero-shot, open-vocabulary 3D semantic mapping by assigning embedding vectors to 2D…

计算机视觉与模式识别 · 计算机科学 2025-12-09 Mohamad Amin Mirzaei , Pantea Amoie , Ali Ekhterachian , Matin Mirzababaei , Babak Khalaj

Semantic segmentation in videos has been a focal point of recent research. However, existing models encounter challenges when faced with unfamiliar categories. To address this, we introduce the Open Vocabulary Video Semantic Segmentation…

多媒体 · 计算机科学 2024-12-13 Xinhao Li , Yun Liu , Guolei Sun , Min Wu , Le Zhang , Ce Zhu

Domain Generalization in Semantic Segmentation (DG-SS) aims to enable segmentation models to perform robustly in unseen environments. However, conventional DG-SS methods are restricted to a fixed set of known categories, limiting their…

计算机视觉与模式识别 · 计算机科学 2026-03-10 Dong Zhao , Qi Zang , Nan Pu , Wenjing Li , Nicu Sebe , Zhun Zhong

Most existing methods for training-free open-vocabulary semantic segmentation are based on CLIP. While these approaches have made progress, they often face challenges in precise localization or require complex pipelines to combine separate…

计算机视觉与模式识别 · 计算机科学 2026-04-23 Kaiyu Li , Shengqi Zhang , Yujie Wang , Yupeng Deng , Zhi Wang , Deyu Meng , Xiangyong Cao

Recent advancements in pre-trained vision-language models, such as CLIP, have enabled the segmentation of arbitrary concepts solely from textual inputs, a process commonly referred to as open-vocabulary semantic segmentation (OVS). However,…

计算机视觉与模式识别 · 计算机科学 2023-07-18 Kunyang Han , Yong Liu , Jun Hao Liew , Henghui Ding , Yunchao Wei , Jiajun Liu , Yitong Wang , Yansong Tang , Yujiu Yang , Jiashi Feng , Yao Zhao

Current point-cloud detection methods have difficulty detecting the open-vocabulary objects in the real world, due to their limited generalization capability. Moreover, it is extremely laborious and expensive to collect and fully annotate a…

计算机视觉与模式识别 · 计算机科学 2022-07-06 Yuheng Lu , Chenfeng Xu , Xiaobao Wei , Xiaodong Xie , Masayoshi Tomizuka , Kurt Keutzer , Shanghang Zhang

Recently, 3D Gaussian Splatting (3DGS) has shown encouraging performance for open vocabulary scene understanding tasks. However, previous methods cannot distinguish 3D instance-level information, which usually predicts a heatmap between the…

计算机视觉与模式识别 · 计算机科学 2025-03-25 Hongjia Zhai , Hai Li , Zhenzhe Li , Xiaokun Pan , Yijia He , Guofeng Zhang

Generalizing open-vocabulary 3D instance segmentation (OV-3DIS) to diverse, unstructured, and mesh-free environments is crucial for robotics and AR/VR, yet remains a significant challenge. We attribute this to two key limitations of…

计算机视觉与模式识别 · 计算机科学 2026-05-15 Zhishan Zhou , Siyuan Wei , Zengran Wang , Chunjie Wang , Xiaosheng Yan , Xiao Liu

Open-vocabulary 3D object detection (OV-3Det) aims to generalize beyond the limited number of base categories labeled during the training phase. The biggest bottleneck is the scarcity of annotated 3D data, whereas 2D image datasets are…

计算机视觉与模式识别 · 计算机科学 2024-11-19 Timing Yang , Yuanliang Ju , Li Yi

Deep learning within the context of point clouds has gained much research interest in recent years mostly due to the promising results that have been achieved on a number of challenging benchmarks, such as 3D shape recognition and scene…

计算机视觉与模式识别 · 计算机科学 2018-12-06 Ye Zhu , Sven Ewan Shepstone , Pablo Martínez-Nuevo , Miklas Strøm Kristoffersen , Fabien Moutarde , Zhuang Fu

Recently, methods have been proposed for 3D open-vocabulary semantic segmentation. Such methods are able to segment scenes into arbitrary classes based on text descriptions provided during runtime. In this paper, we propose to the best of…

计算机视觉与模式识别 · 计算机科学 2024-01-19 Haoran Chen , Kenneth Blomqvist , Francesco Milano , Roland Siegwart

Understanding the 3D semantics of a scene is a fundamental problem for various scenarios such as embodied agents. While NeRFs and 3DGS excel at novel-view synthesis, previous methods for understanding their semantics have been limited to…

计算机视觉与模式识别 · 计算机科学 2025-02-24 Hyunjee Lee , Youngsik Yun , Jeongmin Bae , Seoha Kim , Youngjung Uh

We introduce Open3DIS, a novel solution designed to tackle the problem of Open-Vocabulary Instance Segmentation within 3D scenes. Objects within 3D environments exhibit diverse shapes, scales, and colors, making precise instance-level…

计算机视觉与模式识别 · 计算机科学 2024-04-09 Phuc D. A. Nguyen , Tuan Duc Ngo , Evangelos Kalogerakis , Chuang Gan , Anh Tran , Cuong Pham , Khoi Nguyen

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…

计算机视觉与模式识别 · 计算机科学 2025-12-03 Ziren Gong , Xiaohan Li , Fabio Tosi , Jiawei Han , Stefano Mattoccia , Jianfei Cai , Matteo Poggi

Semantic segmentation of 3D LiDAR point clouds, essential for autonomous driving and infrastructure management, is best achieved by supervised learning, which demands extensive annotated datasets and faces the problem of domain shifts. We…

计算机视觉与模式识别 · 计算机科学 2025-05-07 Andrew Caunes , Thierry Chateau , Vincent Frémont

The deficiency of 3D segmentation labels is one of the main obstacles to effective point cloud segmentation, especially for scenes in the wild with varieties of different objects. To alleviate this issue, we propose a novel deep graph…

计算机视觉与模式识别 · 计算机科学 2020-05-19 Haiyan Wang , Xuejian Rong , Liang Yang , Jinglun Feng , Jizhong Xiao , Yingli Tian

In this paper, we consider the problem of open-vocabulary semantic segmentation (OVS), which aims to segment objects of arbitrary classes instead of pre-defined, closed-set categories. The main contributions are as follows: First, we…

计算机视觉与模式识别 · 计算机科学 2023-03-06 Jilan Xu , Junlin Hou , Yuejie Zhang , Rui Feng , Yi Wang , Yu Qiao , Weidi Xie

In this paper, we propose PASS3D to achieve point-wise semantic segmentation for 3D point cloud. Our framework combines the efficiency of traditional geometric methods with robustness of deep learning methods, consisting of two stages: At…

计算机视觉与模式识别 · 计算机科学 2020-08-27 Xin Kong , Guangyao Zhai , Baoquan Zhong , Yong Liu

Although perception systems have made remarkable advancements in recent years, particularly in 2D reasoning segmentation, these systems still rely on explicit human instruction or pre-defined categories to identify target objects before…

计算机视觉与模式识别 · 计算机科学 2025-06-06 Kunshen Zhang

Recent advances in leveraging large-scale Internet photo collections for 3D reconstruction have enabled immersive virtual exploration of landmarks and historic sites worldwide. However, little attention has been given to the immersive…

图形学 · 计算机科学 2025-08-06 Yuze Wang , Yue Qi