Results 21 to 30 of about 897,519 (241)
DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation [PDF]
International Conference on Learning Representations, 2023 Recent advances in 3D content creation mostly leverage optimization-based 3D generation via score distillation sampling (SDS). Though promising results have been exhibited, these methods often suffer from slow per-sample optimization, limiting their ...
Jiaxiang Tang +4 more
semanticscholar +1 more source
Computer Vision and Pattern Recognition, 2023 We present the first application of 3D Gaussian Splatting in monocular SLAM, the most fundamental but the hardest setup for Visual SLAM. Our method, which runs live at 3fps, utilises Gaussians as the only 3D representation, unifying the required ...
Hidenobu Matsuki +3 more
semanticscholar +1 more source
LangSplat: 3D Language Gaussian Splatting [PDF]
Computer Vision and Pattern Recognition, 2023 Humans live in a 3D world and commonly use natural language to interact with a 3D scene. Modeling a 3D language field to support open-ended language queries in 3D has gained increasing attention recently. This paper introduces LangSplat, which constructs
Minghan Qin +4 more
semanticscholar +1 more source
Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields [PDF]
Computer Vision and Pattern Recognition, 2023 3D scene representations have gained immense popularity in recent years. Methods that use Neural Radiance fields are versatile for traditional tasks such as novel view synthesis.
Shijie Zhou +9 more
semanticscholar +1 more source
SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes [PDF]
Computer Vision and Pattern Recognition, 2023 Novel view synthesis for dynamic scenes is still a challenging problem in computer vision and graphics. Recently, Gaussian splatting has emerged as a robust technique to represent static scenes and enable high-quality and real-time novel view synthesis ...
Yi-Hua Huang +5 more
semanticscholar +1 more source
GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting [PDF]
Computer Vision and Pattern Recognition, 2023 3D editing plays a crucial role in many areas such as gaming and virtual reality. Traditional 3D editing methods, which rely on representations like meshes and point clouds, often fall short in realistically depicting complex scenes.
Yi-Wen Chen +9 more
semanticscholar +1 more source
Gaussian splatting for the reconstruction of complex and highly detailed object [PDF]
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information SciencesIn recent years, Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have emerged as advanced methods for photogrammetry-based 3D reconstruction.
S. Gonizzi Barsanti +5 more
doaj +1 more source
2D Gaussian Splatting for Geometrically Accurate Radiance Fields [PDF]
International Conference on Computer Graphics and Interactive Techniques3D Gaussian Splatting (3DGS) has recently revolutionized radiance field reconstruction, achieving high quality novel view synthesis and fast rendering speed.
Binbin Huang +4 more
semanticscholar +1 more source
GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting [PDF]
Computer Vision and Pattern Recognition, 2023 In this paper, we introduce GS-SLAM that first utilizes 3D Gaussian representation in the Simultaneous Localization and Mapping (SLAM) system. It facilitates a better bal-ance between efficiency and accuracy.
Chi Yan +6 more
semanticscholar +1 more source
A Comprehensive Evaluation of the Spatial Accuracy of Building Gaussian Splatting [PDF]
ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences3D building models are powerful visual tools, typically generated with well-established image-matching or LiDAR methods. However, they do not capture the view-dependent colour characteristics possible with Gaussian splatting. Despite the visual potential
S. McNally +3 more
doaj +1 more source