中文
相关论文

相关论文: Rethinking Pose Refinement in 3D Gaussian Splattin…

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

3D Gaussian Splatting (3DGS) has emerged as a key rendering pipeline for digital asset creation due to its balance between efficiency and visual quality. To address the issues of unstable pose estimation and scene representation distortion…

计算机视觉与模式识别 · 计算机科学 2025-11-11 Meijun Guo , Yongliang Shi , Caiyun Liu , Yixiao Feng , Ming Ma , Tinghai Yan , Weining Lu , Bin Liang

In this paper, we address common error sources for 3D Gaussian Splatting (3DGS) including blur, imperfect camera poses, and color inconsistencies, with the goal of improving its robustness for practical applications like reconstructions…

计算机视觉与模式识别 · 计算机科学 2024-04-08 François Darmon , Lorenzo Porzi , Samuel Rota-Bulò , Peter Kontschieder

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

3D Gaussian Splatting (3DGS) has revolutionized neural rendering with its efficiency and quality, but like many novel view synthesis methods, it heavily depends on accurate camera poses from Structure-from-Motion (SfM) systems. Although…

计算机视觉与模式识别 · 计算机科学 2025-04-08 Zhisheng Huang , Peng Wang , Jingdong Zhang , Yuan Liu , Xin Li , Wenping Wang

3D Gaussian Splatting (3DGS) has emerged as a core technique for 3D representation. Its effectiveness largely depends on precise camera poses and accurate point cloud initialization, which are often derived from pretrained Multi-View Stereo…

计算机视觉与模式识别 · 计算机科学 2025-07-25 Chong Cheng , Zijian Wang , Sicheng Yu , Yu Hu , Nanjie Yao , Hao Wang

Reconstructing dynamic 3D scenes from monocular video has broad applications in AR/VR, robotics, and autonomous navigation, but often fails due to severe motion blur caused by camera and object motion. Existing methods commonly follow a…

计算机视觉与模式识别 · 计算机科学 2026-03-17 Zhijing Wu , Longguang Wang

Recent advances in 3D Gaussian Splatting have enabled impressive photorealistic novel view synthesis. However, to transition from a pure rendering engine to a reliable spatial map for autonomous agents and safety-critical applications,…

计算机视觉与模式识别 · 计算机科学 2026-03-25 Chamuditha Jayanga Galappaththige , Thomas Gottwald , Peter Stehr , Edgar Heinert , Niko Suenderhauf , Dimity Miller , Matthias Rottmann

We propose SelfSplat, a novel 3D Gaussian Splatting model designed to perform pose-free and 3D prior-free generalizable 3D reconstruction from unposed multi-view images. These settings are inherently ill-posed due to the lack of…

计算机视觉与模式识别 · 计算机科学 2025-04-08 Gyeongjin Kang , Jisang Yoo , Jihyeon Park , Seungtae Nam , Hyeonsoo Im , Sangheon Shin , Sangpil Kim , Eunbyung Park

Although various visual localization approaches exist, such as scene coordinate regression and camera pose regression, these methods often struggle with optimization complexity or limited accuracy. To address these challenges, we explore…

计算机视觉与模式识别 · 计算机科学 2025-03-21 Gennady Sidorov , Malik Mohrat , Denis Gridusov , Ruslan Rakhimov , Sergey Kolyubin

3D Gaussian Splatting (3DGS) has achieved impressive rendering performance in novel view synthesis. However, its efficacy diminishes considerably in sparse image sequences, where inherent data sparsity amplifies geometric uncertainty during…

计算机视觉与模式识别 · 计算机科学 2025-03-17 Zhen Tan , Xieyuanli Chen , Jinpu Zhang , Lei Feng , Dewen Hu

The process of 3D scene reconstruction can be affected by numerous uncertainty sources in real-world scenes. While Neural Radiance Fields (NeRFs) and 3D Gaussian Splatting (GS) achieve high-fidelity rendering, they lack built-in mechanisms…

计算机视觉与模式识别 · 计算机科学 2024-09-11 Marcus Klasson , Riccardo Mereu , Juho Kannala , Arno Solin

Recent advances in 3D Gaussian Splatting (3DGS) have focused on accelerating optimization while preserving reconstruction quality. However, many proposed methods entangle implementation-level improvements with fundamental algorithmic…

计算机视觉与模式识别 · 计算机科学 2026-02-11 Florian Hahlbohm , Linus Franke , Martin Eisemann , Marcus Magnor

Recently, generalizable human Gaussian splatting from sparse-view inputs has been actively studied for the photorealistic human rendering. Most existing methods rely on explicit geometric constraints or predefined structural representations…

计算机视觉与模式识别 · 计算机科学 2026-04-29 Jingi Kim , Wonjun Kim

Differentiable 3D Gaussian splatting has emerged as an efficient and flexible rendering technique for representing complex scenes from a collection of 2D views and enabling high-quality real-time novel-view synthesis. However, its reliance…

图形学 · 计算机科学 2025-01-16 Meenakshi Krishnan , Liam Fowl , Ramani Duraiswami

We propose R3GS, a robust reconstruction and relocalization framework tailored for unconstrained datasets. Our method uses a hybrid representation during training. Each anchor combines a global feature from a convolutional neural network…

计算机视觉与模式识别 · 计算机科学 2025-05-22 Xu yan , Zhaohui Wang , Rong Wei , Jingbo Yu , Dong Li , Xiangde Liu

We propose a method to enhance 3D Gaussian Splatting (3DGS)~\cite{Kerbl2023}, addressing challenges in initialization, optimization, and density control. Gaussian Splatting is an alternative for rendering realistic images while supporting…

计算机视觉与模式识别 · 计算机科学 2025-07-02 Xingjun Wang , Lianlei Shan

In this paper, we present a method for localizing a query image with respect to a precomputed 3D Gaussian Splatting (3DGS) scene representation. First, the method uses 3DGS to render a synthetic RGBD image at some initial pose estimate.…

计算机视觉与模式识别 · 计算机科学 2025-05-02 Jongwon Lee , Timothy Bretl

3D Gaussian Splatting (3DGS) under raindrop conditions suffers from severe occlusions and optical distortions caused by raindrop contamination on the camera lens, substantially degrading reconstruction quality. Existing benchmarks typically…

计算机视觉与模式识别 · 计算机科学 2025-12-30 Zhiqiang Teng , Tingting Chen , Beibei Lin , Zifeng Yuan , Xuanyi Li , Xuanyu Zhang , Shunli Zhang

Recent advances in 3D Gaussian Splatting (3DGS) have enabled high-quality, real-time novel-view synthesis from multi-view images. However, most existing methods assume the object is captured in a single, static pose, resulting in incomplete…

计算机视觉与模式识别 · 计算机科学 2025-10-20 Ting-Yu Yen , Yu-Sheng Chiu , Shih-Hsuan Hung , Peter Wonka , Hung-Kuo Chu
‹ 上一页 1 2 3 10 下一页 ›