中文
相关论文

相关论文: CAGS: Open-Vocabulary 3D Scene Understanding with …

200 篇论文

Recently, reconstructing scenes from a single panoramic image using advanced 3D Gaussian Splatting (3DGS) techniques has attracted growing interest. Panoramic images offer a 360$\times$ 180 field of view (FoV), capturing the entire scene in…

计算机视觉与模式识别 · 计算机科学 2025-04-15 Zhijie Shen , Chunyu Lin , Shujuan Huang , Lang Nie , Kang Liao , Yao Zhao

Image representation is a fundamental task in computer vision. Recently, Gaussian Splatting has emerged as an efficient representation framework, and its extension to 2D image representation enables lightweight, yet expressive modeling of…

计算机视觉与模式识别 · 计算机科学 2025-12-30 Masaya Takabe , Hiroshi Watanabe , Sujun Hong , Tomohiro Ikai , Zheming Fan , Ryo Ishimoto , Kakeru Sugimoto , Ruri Imichi

Dynamic scene reconstruction is a long-term challenge in the field of 3D vision. Recently, the emergence of 3D Gaussian Splatting has provided new insights into this problem. Although subsequent efforts rapidly extend static 3D Gaussian to…

计算机视觉与模式识别 · 计算机科学 2024-10-11 Ruijie Zhu , Yanzhe Liang , Hanzhi Chang , Jiacheng Deng , Jiahao Lu , Wenfei Yang , Tianzhu Zhang , Yongdong Zhang

Recent advancements in dynamic 3D scene reconstruction have shown promising results, enabling high-fidelity 3D novel view synthesis with improved temporal consistency. Among these, 4D Gaussian Splatting (4DGS) has emerged as an appealing…

计算机视觉与模式识别 · 计算机科学 2025-05-20 Seungjun Oh , Younggeun Lee , Hyejin Jeon , Eunbyung Park

3D Gaussian Splatting (3DGS) is a highly deployable real-time method for novel view synthesis. In practice, it requires a universal, consistent control mechanism that adjusts the trade-off between rendering quality and model compression…

计算机视觉与模式识别 · 计算机科学 2025-11-10 Fengdi Zhang , Yibao Sun , Hongkun Cao , Ruqi Huang

Modeling 3D language fields with Gaussian Splatting for open-ended language queries has recently garnered increasing attention. However, recent 3DGS-based models leverage view-dependent 2D foundation models to refine 3D semantics but lack a…

计算机视觉与模式识别 · 计算机科学 2025-06-10 Chenlu Zhan , Yufei Zhang , Gaoang Wang , Hongwei Wang

Recent advancements in 3D reconstruction coupled with neural rendering techniques have greatly improved the creation of photo-realistic 3D scenes, influencing both academic research and industry applications. The technique of 3D Gaussian…

计算机视觉与模式识别 · 计算机科学 2026-03-19 Zexu Huang , Min Xu , Stuart Perry

Reconstructing dynamic 3D urban scenes is crucial for autonomous driving, yet current methods face a stark trade-off between fidelity and computational cost. This inefficiency stems from their semantically agnostic design, which allocates…

计算机视觉与模式识别 · 计算机科学 2025-10-15 Ying A , Wenzhang Sun , Chang Zeng , Chunfeng Wang , Hao Li , Jianxun Cui

Novel view synthesis has demonstrated impressive progress recently, with 3D Gaussian splatting (3DGS) offering efficient training time and photorealistic real-time rendering. However, reliance on Cartesian coordinates limits 3DGS's…

图形学 · 计算机科学 2025-03-26 Xinpeng Liu , Zeyi Huang , Fumio Okura , Yasuyuki Matsushita

Maintaining consistent 3D scene representations over time is a significant challenge in computer vision. Updating 3D scenes from sparse-view observations is crucial for various real-world applications, including urban planning, disaster…

计算机视觉与模式识别 · 计算机科学 2025-12-02 Zeyuan An , Yanghang Xiao , Zhiying Leng , Frederick W. B. Li , Xiaohui Liang

Robotics applications often rely on scene reconstructions to enable downstream tasks. In this work, we tackle the challenge of actively building an accurate map of an unknown scene using an RGB-D camera on a mobile platform. We propose a…

机器人学 · 计算机科学 2025-04-09 Liren Jin , Xingguang Zhong , Yue Pan , Jens Behley , Cyrill Stachniss , Marija Popović

3D Shape represented as point cloud has achieve advancements in multimodal pre-training to align image and language descriptions, which is curial to object identification, classification, and retrieval. However, the discrete representations…

计算机视觉与模式识别 · 计算机科学 2024-02-14 Haoyuan Li , Yanpeng Zhou , Yihan Zeng , Hang Xu , Xiaodan Liang

Modeling open-vocabulary language fields in 3D is essential for intuitive human-AI interaction and querying within physical environments. State-of-the-art approaches, such as LangSplat, leverage 3D Gaussian Splatting to efficiently…

计算机视觉与模式识别 · 计算机科学 2025-10-28 Pranav Saxena

The accurate reconstruction of dynamic street scenes is critical for applications in autonomous driving, augmented reality, and virtual reality. Traditional methods relying on dense point clouds and triangular meshes struggle with moving…

计算机视觉与模式识别 · 计算机科学 2026-05-05 Peizhen Zheng , Dongjing Jiang , Qingchong Jiao , Redouane EL Bouchtaoui , Flynnwell Jianfei Zhang

Open-vocabulary 3D Scene Graph (3DSG) can enhance various downstream tasks in robotics by leveraging structured semantic representations, yet current 3DSG construction methods suffer from semantic inconsistencies caused by noisy cross-image…

计算机视觉与模式识别 · 计算机科学 2026-03-17 Yue Chang , Rufeng Chen , Zhaofan Zhang , Yi Chen , Yifan Tian , Sihong Xie

With the emergence of Gaussian Splats, recent efforts have focused on large-scale scene geometric reconstruction. However, most of these efforts either concentrate on memory reduction or spatial space division, neglecting information in the…

计算机视觉与模式识别 · 计算机科学 2024-05-29 Butian Xiong , Xiaoyu Ye , Tze Ho Elden Tse , Kai Han , Shuguang Cui , Zhen Li

Representing 3D scenes from multiview images is a core challenge in computer vision and graphics, which requires both precise rendering and accurate reconstruction. Recently, 3D Gaussian Splatting (3DGS) has garnered significant attention…

计算机视觉与模式识别 · 计算机科学 2025-03-04 You Shen , Zhipeng Zhang , Xinyang Li , Yansong Qu , Yu Lin , Shengchuan Zhang , Liujuan Cao

Open-vocabulary 3D segmentation is a fundamental yet challenging task, requiring a mutual understanding of both segmentation and language. However, existing Gaussian-splatting-based methods rely either on a single 3D language field, leading…

计算机视觉与模式识别 · 计算机科学 2025-10-24 Runsong Zhu , Ka-Hei Hui , Zhengzhe Liu , Qianyi Wu , Weiliang Tang , Shi Qiu , Pheng-Ann Heng , Chi-Wing Fu

Recent advances in 3D Gaussian Splatting have shown remarkable potential for novel view synthesis. However, most existing large-scale scene reconstruction methods rely on the divide-and-conquer paradigm, which often leads to the loss of…

计算机视觉与模式识别 · 计算机科学 2025-05-30 Chuandong Liu , Huijiao Wang , Lei Yu , Gui-Song Xia

In the domain of 3D scene representation, 3D Gaussian Splatting (3DGS) has emerged as a pivotal technology. However, its application to large-scale, high-resolution scenes (exceeding 4k$\times$4k pixels) is hindered by the excessive…

计算机视觉与模式识别 · 计算机科学 2024-04-22 Wenkai Liu , Tao Guan , Bin Zhu , Lili Ju , Zikai Song , Dan Li , Yuesong Wang , Wei Yang