中文
相关论文

相关论文: Quadratic Gaussian Splatting: High Quality Surface…

200 篇论文

3D Gaussian Splatting produces high-quality scene reconstructions but generates hundreds of thousands of spurious Gaussians (floaters) scattered throughout the environment. These artifacts obscure objects of interest and inflate model…

计算机视觉与模式识别 · 计算机科学 2026-01-06 Subhankar Mishra

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

2D Gaussian Splatting has recently emerged as a significant method in 3D reconstruction, enabling novel view synthesis and geometry reconstruction simultaneously. While the well-known Gaussian kernel is broadly used, its lack of anisotropy…

计算机视觉与模式识别 · 计算机科学 2024-09-02 Ruihan Yu , Tianyu Huang , Jingwang Ling , Feng Xu

Previous surface reconstruction methods either suffer from low geometric accuracy or lengthy training times when dealing with real-world complex dynamic scenes involving multi-person activities, and human-object interactions. To tackle the…

计算机视觉与模式识别 · 计算机科学 2024-09-30 Shuo Wang , Binbin Huang , Ruoyu Wang , Shenghua Gao

This paper tackles the intricate challenge of object removal to update the radiance field using the 3D Gaussian Splatting. The main challenges of this task lie in the preservation of geometric consistency and the maintenance of texture…

计算机视觉与模式识别 · 计算机科学 2024-04-23 Yuxin Wang , Qianyi Wu , Guofeng Zhang , Dan Xu

Recently, Gaussian splatting has emerged as a strong alternative to NeRF, demonstrating impressive 3D modeling capabilities while requiring only a fraction of the training and rendering time. In this paper, we show how the standard Gaussian…

计算机视觉与模式识别 · 计算机科学 2025-03-25 Luca Savant Aira , Gabriele Facciolo , Thibaud Ehret

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

Underwater 3D reconstruction and appearance restoration are hindered by the complex optical properties of water, such as wavelength-dependent attenuation and scattering. Existing Neural Radiance Fields (NeRF)-based methods struggle with…

计算机视觉与模式识别 · 计算机科学 2026-01-28 Xinrui Zhang , Yufeng Wang , Shuangkang Fang , Zesheng Wang , Dacheng Qi , Wenrui Ding

Image data captured outdoors often exhibit unbounded scenes and unconstrained, varying lighting conditions, making it challenging to decompose them into geometry, reflectance, and illumination. Recent works have focused on achieving this…

计算机视觉与模式识别 · 计算机科学 2025-09-16 Lianjun Liao , Chunhui Zhang , Tong Wu , Henglei Lv , Bailin Deng , Lin Gao

3D Gaussian Splatting (3DGS) has revolutionized 3D scene representation with superior efficiency and quality. While recent adaptations for computed tomography (CT) show promise, they struggle with severe artifacts under highly sparse-view…

计算机视觉与模式识别 · 计算机科学 2026-02-13 Yuxiang Zhong , Jun Wei , Chaoqi Chen , Senyou An , Hui Huang

High-fidelity reconstruction of dynamic scenes is an important yet challenging problem. While recent 4D Gaussian Splatting (4DGS) has demonstrated the ability to model temporal dynamics, it couples Gaussian motion and geometric attributes…

计算机视觉与模式识别 · 计算机科学 2026-05-19 Yi Zhang , Yulei Kang , Jiangxin Sun , Beihao Xia , Jisheng Dang , Jian-Fang Hu

Recently, 3D Gaussian Splatting (3DGS) has excelled in novel view synthesis (NVS) with its real-time rendering capabilities and superior quality. However, it encounters challenges for high-resolution novel view synthesis (HRNVS) due to the…

计算机视觉与模式识别 · 计算机科学 2025-05-27 Shiyun Xie , Zhiru Wang , Yinghao Zhu , Xu Wang , Chengwei Pan , Xiwang Dong

Precipitation forecasting relies on heterogeneous data. Weather radar is accurate, but coverage is geographically limited and costly to maintain. Weather stations provide accurate but sparse point measurements, while satellites offer dense,…

计算机视觉与模式识别 · 计算机科学 2026-03-03 Doyi Kim , Minseok Seo , Changick Kim

Recent advances in neural rendering, particularly 3D Gaussian Splatting (3DGS), have enabled real-time rendering of complex scenes. However, standard 3DGS relies on spherical harmonics, which often struggle to accurately capture…

量子物理 · 物理学 2026-02-06 Grzegorz Wilczyński , Rafał Tobiasz , Paweł Gora , Marcin Mazur , Przemysław Spurek

High-resolution remote sensing images (RSIs) are crucial for Earth observation applications, yet acquiring them is often limited by sensor constraints and costs. In recent years, generative super-resolution (SR) methods, particularly…

计算机视觉与模式识别 · 计算机科学 2026-05-22 Jiangwei Mo , Xi Lu , Hanlin Wu

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

Implicit neural representations (INRs) have achieved remarkable success in image representation and compression, but they require substantial training time and memory. Meanwhile, recent 2D Gaussian Splatting (GS) methods (\textit{e.g.},…

计算机视觉与模式识别 · 计算机科学 2026-01-01 Tiantian Li , Xinjie Zhang , Xingtong Ge , Tongda Xu , Dailan He , Jun Zhang , Yan Wang

3D Gaussian Splatting (3DGS) enables efficient reconstruction and high-fidelity real-time rendering of complex scenes on consumer hardware. However, due to its rasterization-based formulation, 3DGS is constrained to ideal pinhole cameras…

图形学 · 计算机科学 2025-03-26 Qi Wu , Janick Martinez Esturo , Ashkan Mirzaei , Nicolas Moenne-Loccoz , Zan Gojcic

The emergence of 3D Gaussian Splatting (3D-GS) has significantly advanced 3D reconstruction by providing high fidelity and fast training speeds across various scenarios. While recent efforts have mainly focused on improving model structures…

图形学 · 计算机科学 2025-03-07 Yifei Gao , Jun Huang , Lei Wang , Ruiting Dai , Jun Cheng

The advent of 3D Gaussian Splatting (3D-GS) techniques and their dynamic scene modeling variants, 4D-GS, offers promising prospects for real-time rendering of dynamic surgical scenarios. However, the prerequisite for modeling dynamic scenes…

计算机视觉与模式识别 · 计算机科学 2024-06-25 Hengyu Liu , Yifan Liu , Chenxin Li , Wuyang Li , Yixuan Yuan