中文
相关论文

相关论文: MVGS: Multi-view Regulated Gaussian Splatting for …

200 篇论文

3D Gaussian splatting (3D-GS) is a new rendering approach that outperforms the neural radiance field (NeRF) in terms of both speed and image quality. 3D-GS represents 3D scenes by utilizing millions of 3D Gaussians and projects these…

计算机视觉与模式识别 · 计算机科学 2024-09-26 Joongho Jo , Hyeongwon Kim , Jongsun Park

X-ray is widely applied for transmission imaging due to its stronger penetration than natural light. When rendering novel view X-ray projections, existing methods mainly based on NeRF suffer from long training time and slow inference speed.…

图像与视频处理 · 电气工程与系统科学 2024-10-29 Yuanhao Cai , Yixun Liang , Jiahao Wang , Angtian Wang , Yulun Zhang , Xiaokang Yang , Zongwei Zhou , Alan Yuille

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

We present a Gaussian Splatting method for surface reconstruction using sparse input views. Previous methods relying on dense views struggle with extremely sparse Structure-from-Motion points for initialization. While learning-based…

计算机视觉与模式识别 · 计算机科学 2025-04-30 Jiang Wu , Rui Li , Yu Zhu , Rong Guo , Jinqiu Sun , Yanning Zhang

Referenced-based scene stylization that edits the appearance based on a content-aligned reference image is an emerging research area. Starting with a pretrained neural radiance field (NeRF), existing methods typically learn a novel…

计算机视觉与模式识别 · 计算机科学 2024-07-11 Yiqun Mei , Jiacong Xu , Vishal M. Patel

In recent years, Neural Radiance Fields (NeRF) has revolutionized three-dimensional (3D) reconstruction with its implicit representation. Building upon NeRF, 3D Gaussian Splatting (3D-GS) has departed from the implicit representation of…

计算机视觉与模式识别 · 计算机科学 2024-05-29 Bin Zhang , Bi Zeng , Zexin Peng

3D Gaussian splatting enables high-quality novel view synthesis (NVS) at real-time frame rates. However, its quality drops sharply as we depart from the training views. Thus, dense captures are needed to match the high-quality expectations…

While neural rendering has led to impressive advances in scene reconstruction and novel view synthesis, it relies heavily on accurately pre-computed camera poses. To relax this constraint, multiple efforts have been made to train Neural…

计算机视觉与模式识别 · 计算机科学 2024-07-31 Yang Fu , Sifei Liu , Amey Kulkarni , Jan Kautz , Alexei A. Efros , Xiaolong Wang

We present a novel approach for enhancing the resolution and geometric fidelity of 3D Gaussian Splatting (3DGS) beyond native training resolution. Current 3DGS methods are fundamentally limited by their input resolution, producing…

图形学 · 计算机科学 2025-06-10 Shuja Khalid , Mohamed Ibrahim , Yang Liu

Recently, 3D Gaussian Splatting (3DGS) has emerged as an efficient approach for accurately representing scenes. However, despite its superior novel view synthesis capabilities, extracting the geometry of the scene directly from the Gaussian…

计算机视觉与模式识别 · 计算机科学 2024-07-18 Yaniv Wolf , Amit Bracha , Ron Kimmel

3D Gaussian Splatting has emerged as a very promising scene representation, achieving state-of-the-art quality in novel view synthesis significantly faster than competing alternatives. However, its use of spherical harmonics to represent…

计算机视觉与模式识别 · 计算机科学 2024-10-01 T. Berriel Martins , Javier Civera

Novel view synthesis is a fundamental task in 3D computer vision that aims to reconstruct photorealistic images from novel viewpoints given a set of posed images. However, reconstruction quality degrades sharply under sparse-view conditions…

计算机视觉与模式识别 · 计算机科学 2026-04-03 Wenjun Lu , Haodong Chen , Anqi Yi , Guoxi Huang , Yuk Ying Chung , Kun Hu , Zhiyong Wang

Existing Gaussian splatting methods often fall short in achieving satisfactory novel view synthesis in driving scenes, primarily due to the absence of crafty designs and geometric constraints for the involved elements. This paper introduces…

计算机视觉与模式识别 · 计算机科学 2024-08-20 Xi Shi , Lingli Chen , Peng Wei , Xi Wu , Tian Jiang , Yonggang Luo , Lecheng Xie

When performing 3D inpainting using novel-view rendering methods like Neural Radiance Field (NeRF) or 3D Gaussian Splatting (3DGS), how to achieve texture and geometry consistency across camera views has been a challenge. In this paper, we…

计算机视觉与模式识别 · 计算机科学 2025-04-29 Sheng-Yu Huang , Zi-Ting Chou , Yu-Chiang Frank Wang

In this work, we introduce UniGS, a novel 3D Gaussian reconstruction and novel view synthesis model that predicts a high-fidelity representation of 3D Gaussians from arbitrary number of posed sparse-view images. Previous methods often…

计算机视觉与模式识别 · 计算机科学 2025-04-02 Jiamin Wu , Kenkun Liu , Yukai Shi , Xiaoke Jiang , Yuan Yao , Lei Zhang

In this paper, we present a method to optimize Gaussian splatting with a limited number of images while avoiding overfitting. Representing a 3D scene by combining numerous Gaussian splats has yielded outstanding visual quality. However, it…

计算机视觉与模式识别 · 计算机科学 2024-01-05 Jaeyoung Chung , Jeongtaek Oh , Kyoung Mu Lee

While the field of 3D scene reconstruction is dominated by NeRFs due to their photorealistic quality, 3D Gaussian Splatting (3DGS) has recently emerged, offering similar quality with real-time rendering speeds. However, both methods…

计算机视觉与模式识别 · 计算机科学 2024-11-01 Jonas Kulhanek , Songyou Peng , Zuzana Kukelova , Marc Pollefeys , Torsten Sattler

Feed-forward surround-view autonomous driving scene reconstruction offers fast, generalizable inference ability, which faces the core challenge of ensuring generalization while elevating novel view quality. Due to the surround-view with…

计算机视觉与模式识别 · 计算机科学 2025-10-23 Junhong Lin , Kangli Wang , Shunzhou Wang , Songlin Fan , Ge Li , Wei Gao

3D Gaussian Splatting (3DGS) enables high-quality novel view synthesis, motivating interest in generating higher-resolution renders than those available during training. A natural strategy is to apply super-resolution (SR) to low-resolution…

计算机视觉与模式识别 · 计算机科学 2026-04-01 Pranav Asthana , Alex Hanson , Allen Tu , Tom Goldstein , Matthias Zwicker , Amitabh Varshney

Neural Radiance Field (NeRF) and 3D Gaussian Splatting (3DGS) have noticeably advanced photo-realistic novel view synthesis using images from densely spaced camera viewpoints. However, these methods struggle in few-shot scenarios due to…

计算机视觉与模式识别 · 计算机科学 2025-03-25 Yulong Zheng , Zicheng Jiang , Shengfeng He , Yandu Sun , Junyu Dong , Huaidong Zhang , Yong Du