中文
相关论文

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

200 篇论文

Camera pose refinement aims at improving the accuracy of initial pose estimation for applications in 3D computer vision. Most refinement approaches rely on 2D-3D correspondences with specific descriptors or dedicated networks, requiring…

计算机视觉与模式识别 · 计算机科学 2025-08-26 Lulu Hao , Lipu Zhou , Zhenzhong Wei , Xu Wang

The recently developed Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have shown encouraging and impressive results for visual SLAM. However, most representative methods require RGBD sensors and are only available for indoor…

计算机视觉与模式识别 · 计算机科学 2025-05-16 Zhe Xin , Chenyang Wu , Penghui Huang , Yanyong Zhang , Yinian Mao , Guoquan Huang

High-quality scene reconstruction and novel view synthesis based on Gaussian Splatting (3DGS) typically require steady, high-quality photographs, often impractical to capture with handheld cameras. We present a method that adapts to camera…

计算机视觉与模式识别 · 计算机科学 2024-07-18 Otto Seiskari , Jerry Ylilammi , Valtteri Kaatrasalo , Pekka Rantalankila , Matias Turkulainen , Juho Kannala , Esa Rahtu , Arno Solin

3D Gaussian Splatting has recently emerged as an efficient solution for high-quality and real-time novel view synthesis. However, its capability for accurate surface reconstruction remains underexplored. Due to the discrete and unstructured…

计算机视觉与模式识别 · 计算机科学 2025-11-27 Qing Li , Huifang Feng , Xun Gong , Yu-Shen Liu

For high-level geo-spatial applications and intelligent robotics, accurate global pose information is of crucial importance. Map-aided localization is a universal approach to overcome the limitations of global navigation satellite system…

机器人学 · 计算机科学 2025-11-19 Yuxuan Zhou , Xingxing Li , Shengyu Li , Chunxi Xia , Xuanbin Wang , Shaoquan Feng

Monocular object pose estimation, as a pivotal task in computer vision and robotics, heavily depends on accurate 2D-3D correspondences, which often demand costly CAD models that may not be readily available. Object 3D reconstruction methods…

计算机视觉与模式识别 · 计算机科学 2024-09-05 Luqing Luo , Shichu Sun , Jiangang Yang , Linfang Zheng , Jinwei Du , Jian Liu

Rendering novel view images in dynamic scenes is a crucial yet challenging task. Current methods mainly utilize NeRF-based methods to represent the static scene and an additional time-variant MLP to model scene deformations, resulting in…

计算机视觉与模式识别 · 计算机科学 2024-06-07 Diwen Wan , Ruijie Lu , Gang Zeng

Gaussian Splatting has emerged as a high-performance technique for novel view synthesis, enabling real-time rendering and high-quality reconstruction of small scenes. However, scaling to larger environments has so far relied on partitioning…

3D scene reconstruction and rendering are core tasks in computer vision, with applications spanning industrial monitoring, robotics, and autonomous driving. Recent advances in 3D Gaussian Splatting (GS) and its variants have achieved…

计算机视觉与模式识别 · 计算机科学 2026-02-20 Chi-Shiang Gau , Konstantinos D. Polyzos , Athanasios Bacharis , Saketh Madhuvarasu , Tara Javidi

3D Gaussian splatting (3DGS) has recently emerged as an alternative representation that leverages a 3D Gaussian-based representation and introduces an approximated volumetric rendering, achieving very fast rendering speed and promising…

计算机视觉与模式识别 · 计算机科学 2024-08-08 Joo Chan Lee , Daniel Rho , Xiangyu Sun , Jong Hwan Ko , Eunbyung Park

Jointly estimating camera poses and mapping scenes from RGBD images is a fundamental task in simultaneous localization and mapping (SLAM). State-of-the-art methods employ 3D Gaussians to represent a scene, and render these Gaussians through…

计算机视觉与模式识别 · 计算机科学 2025-06-04 Pengchong Hu , Zhizhong Han

While Gaussian Splatting-based Feature Fields (GSFFs) have shown promise for visual localization, this paper highlights that photometrically optimized GSFFs are inherently ill-suited for 2D-3D matching. The volumetric extent of each…

计算机视觉与模式识别 · 计算机科学 2026-05-11 Miso Lee , Sangeek Hyun , Yerim Jeon , Jae-Pil Heo

Capturing 4D spatiotemporal surroundings is crucial for the safe and reliable operation of robots in dynamic environments. However, most existing methods address only one side of the problem: they either provide coarse geometric tracking…

计算机视觉与模式识别 · 计算机科学 2026-02-27 Maximilian Luz , Rohit Mohan , Thomas Nürnberg , Yakov Miron , Daniele Cattaneo , Abhinav Valada

3D Gaussian Splatting (3DGS) is a powerful reconstruction technique, but it needs to be initialized from accurate camera poses and high-fidelity point clouds. Typically, the initialization is taken from Structure-from-Motion (SfM)…

计算机视觉与模式识别 · 计算机科学 2025-04-15 Jizong Peng , Tze Ho Elden Tse , Kai Xu , Wenchao Gao , Angela Yao

We present a dense simultaneous localization and mapping (SLAM) method that uses 3D Gaussians as a scene representation. Our approach enables interactive-time reconstruction and photo-realistic rendering from real-world single-camera RGBD…

计算机视觉与模式识别 · 计算机科学 2024-03-25 Vladimir Yugay , Yue Li , Theo Gevers , Martin R. Oswald

3D Gaussian Splatting (3DGS) has shown remarkable success in synthesizing novel views given multiple views of a static scene. Yet, 3DGS faces challenges when applied to dynamic scenes because 3D Gaussian parameters need to be updated per…

图形学 · 计算机科学 2024-07-08 Kai Katsumata , Duc Minh Vo , Hideki Nakayama

Handling the dynamic environments is a significant research challenge in Visual Simultaneous Localization and Mapping (SLAM). Recent research combines 3D Gaussian Splatting (3DGS) with SLAM to achieve both robust camera pose estimation and…

计算机视觉与模式识别 · 计算机科学 2026-04-29 Yunsong Wang , Gim Hee Lee

We introduce LighthouseGS, a practical novel view synthesis framework based on 3D Gaussian Splatting that utilizes simple panorama-style captures from a single mobile device. While convenient, this rotation-dominant motion and narrow…

图形学 · 计算机科学 2026-02-12 Seungoh Han , Jaehoon Jang , Hyunsu Kim , Jaeheung Surh , Junhyung Kwak , Hyowon Ha , Kyungdon Joo

3D Gaussian Splatting is emerging as a state-of-the-art technique in novel view synthesis, recognized for its impressive balance between visual quality, speed, and rendering efficiency. However, reliance on third-degree spherical harmonics…

计算机视觉与模式识别 · 计算机科学 2025-01-03 Yiwen Wang , Siyuan Chen , Ran Yi

3D occupancy prediction is critical for comprehensive scene understanding in vision-centric autonomous driving. Recent advances have explored utilizing 3D semantic Gaussians to model occupancy while reducing computational overhead, but they…

计算机视觉与模式识别 · 计算机科学 2026-02-27 Xiaoyang Yan , Muleilan Pei , Shaojie Shen