中文
相关论文

相关论文: LoGS: Visual Localization via Gaussian Splatting w…

200 篇论文

Simultaneous Localization and Mapping (SLAM) is a critical task that enables autonomous vehicles to construct maps and localize themselves in unknown environments. Recent breakthroughs combine SLAM with 3D Gaussian Splatting (3DGS) to…

硬件体系结构 · 计算机科学 2025-09-03 Houshu He , Naifeng Jing , Li Jiang , Xiaoyao Liang , Zhuoran Song

Building semantic 3D maps is valuable for searching for objects of interest in offices, warehouses, stores, and homes. We present a mapping system that incrementally builds a Language-Embedded Gaussian Splat (LEGS): a detailed 3D scene…

Recent advances in 3D Gaussian Splatting (3DGS) deliver striking photorealism, and extending it to large scenes opens new opportunities for semantic reasoning and prediction in applications such as autonomous driving. Today's…

计算机视觉与模式识别 · 计算机科学 2026-02-24 Shengkai Zhang , Yuhe Liu , Jianhua He , Xuedou Xiao , Mozi Chen , Kezhong Liu

Gaussian Splatting (GS) has significantly elevated scene reconstruction efficiency and novel view synthesis (NVS) accuracy compared to Neural Radiance Fields (NeRF), particularly for dynamic scenes. However, current 4D NVS methods, whether…

计算机视觉与模式识别 · 计算机科学 2025-04-02 Fang Li , Hao Zhang , Narendra Ahuja

Deformable Gaussian Splatting (GS) accomplishes photorealistic dynamic 3-D reconstruction from dense multi-view video (MVV) by learning to deform a canonical GS representation. However, in filmmaking, tight budgets can result in sparse…

计算机视觉与模式识别 · 计算机科学 2026-04-21 Adrian Azzarelli , Nantheera Anantrasirichai , David R Bull

This paper presents a pose-free, feed-forward 3D Gaussian Splatting (3DGS) framework designed to handle unfavorable input views. A common rendering setup for training feed-forward approaches places a 3D object at the world origin and…

计算机视觉与模式识别 · 计算机科学 2025-08-07 Yuki Fujimura , Takahiro Kushida , Kazuya Kitano , Takuya Funatomi , Yasuhiro Mukaigawa

Visual (re)localization is critical for various applications in computer vision and robotics. Its goal is to estimate the 6 degrees of freedom (DoF) camera pose for each query image, based on a set of posed database images. Currently, all…

计算机视觉与模式识别 · 计算机科学 2023-07-20 Siyan Dong , Shaohui Liu , Hengkai Guo , Baoquan Chen , Marc Pollefeys

Reconstructing high-quality 3D models from sparse 2D images has garnered significant attention in computer vision. Recently, 3D Gaussian Splatting (3DGS) has gained prominence due to its explicit representation with efficient training speed…

计算机视觉与模式识别 · 计算机科学 2024-12-31 Keng-Wei Chang , Zi-Ming Wang , Shang-Hong Lai

Recently, 3D Gaussian Splatting (3DGS) has enabled photorealistic view synthesis at high inference speeds. However, its splatting-based rendering model makes several approximations to the rendering equation, reducing physical accuracy. We…

计算机视觉与模式识别 · 计算机科学 2025-05-22 Chinmay Talegaonkar , Yash Belhe , Ravi Ramamoorthi , Nicholas Antipa

The semantic synthesis of unseen scenes from multiple viewpoints is crucial for research in 3D scene understanding. Current methods are capable of rendering novel-view images and semantic maps by reconstructing generalizable Neural Radiance…

图形学 · 计算机科学 2025-05-09 Feng Xiao , Hongbin Xu , Wanlin Liang , Wenxiong Kang

3D Gaussian Splatting (3DGS) has gained significant attention for its application in dense Simultaneous Localization and Mapping (SLAM), enabling real-time rendering and high-fidelity mapping. However, existing 3DGS-based SLAM methods often…

机器人学 · 计算机科学 2024-09-18 Ziheng Xu , Qingfeng Li , Chen Chen , Xuefeng Liu , Jianwei Niu

Free-Viewpoint Video (FVV) reconstruction enables photorealistic and interactive 3D scene visualization; however, real-time streaming is often bottlenecked by sparse-view inputs, prohibitive training costs, and bandwidth constraints. While…

图形学 · 计算机科学 2026-01-27 Xinhui Liu , Can Wang , Lei Liu , Zhenghao Chen , Wei Jiang , Wei Wang , Dong Xu

Recently, 3D Gaussian Spatting (3DGS) has gained widespread attention in Novel View Synthesis (NVS) due to the remarkable real-time rendering performance. However, the substantial cost of storage and transmission of vanilla 3DGS hinders its…

计算机视觉与模式识别 · 计算机科学 2025-04-01 Jingui Ma , Yang Hu , Luyang Tang , Jiayu Yang , Yongqi Zhai , Ronggang Wang

Abstract representations of 3D scenes play a crucial role in computer vision, enabling a wide range of applications such as mapping, localization, surface reconstruction, and even advanced tasks like SLAM and rendering. Among these…

计算机视觉与模式识别 · 计算机科学 2024-12-16 Chenggang Yang , Yuang Shi

This paper presents GGRt, a novel approach to generalizable novel view synthesis that alleviates the need for real camera poses, complexity in processing high-resolution images, and lengthy optimization processes, thus facilitating stronger…

计算机视觉与模式识别 · 计算机科学 2024-05-13 Hao Li , Yuanyuan Gao , Chenming Wu , Dingwen Zhang , Yalun Dai , Chen Zhao , Haocheng Feng , Errui Ding , Jingdong Wang , Junwei Han

Conventional geometry-based SLAM systems lack dense 3D reconstruction capabilities since their data association usually relies on feature correspondences. Additionally, learning-based SLAM systems often fall short in terms of real-time…

计算机视觉与模式识别 · 计算机科学 2024-08-22 Zhongche Qu , Zhi Zhang , Cong Liu , Jianhua Yin

Standard 3D Gaussian Splatting (3DGS) relies on known or pre-computed camera poses and a sparse point cloud, obtained from structure-from-motion (SfM) preprocessing, to initialize and grow 3D Gaussians. We propose a novel SfM-Free 3DGS…

计算机视觉与模式识别 · 计算机科学 2024-12-03 Bo Ji , Angela Yao

Existing visual localization methods are typically either 2D image-based, which are easy to build and maintain but limited in effective geometric reasoning, or 3D structure-based, which achieve high accuracy but require a centralized…

计算机视觉与模式识别 · 计算机科学 2026-01-08 Xudong Jiang , Fangjinhua Wang , Silvano Galliani , Christoph Vogel , Marc Pollefeys

This paper presents Planar Gaussian Splatting (PGS), a novel neural rendering approach to learn the 3D geometry and parse the 3D planes of a scene, directly from multiple RGB images. The PGS leverages Gaussian primitives to model the scene…

计算机视觉与模式识别 · 计算机科学 2024-12-04 Farhad G. Zanjani , Hong Cai , Hanno Ackermann , Leila Mirvakhabova , Fatih Porikli

3D Gaussian Splatting (3DGS) has emerged as a powerful representation for neural scene reconstruction, offering high-quality novel view synthesis while maintaining computational efficiency. In this paper, we extend the capabilities of 3DGS…

计算机视觉与模式识别 · 计算机科学 2025-06-10 Jens Piekenbrinck , Christian Schmidt , Alexander Hermans , Narunas Vaskevicius , Timm Linder , Bastian Leibe