Results 61 to 70 of about 2,779 (212)
Time‐Varying 3D Gaussian Splatting Representation for Dynamic Scenes
IET Image Processing, Volume 20, Issue 1, January/December 2026.Explicit polynomial motion and smooth rotation within the lifespan are employed to model dynamic scenes. The density control strategy based on 4D spatiotemporal and contribution scores enhances image details. Photorealistic rendering quality with real‐time performance at 160 FPS on the Neural 3D Video dataset.
Yunbiao Liu +4 more
wiley +1 more source
Scalable 3D video of dynamic scenes [PDF]
, 2018 In this paper we present a scalable 3D video framework for capturing and rendering dynamic scenes. The acquisition system is based on multiple sparsely placed 3D video bricks, each comprising a projector, two grayscale cameras, and a color camera ...
Cotting, Daniel +4 more
core
Brain explorer for connectomic analysis [PDF]
, 2017 Visualization plays a vital role in the analysis of multimodal neuroimaging data. A major challenge in neuroimaging visualization is how to integrate structural, functional, and connectivity data to form a comprehensive visual context for data ...
Andrew J. Saykin +10 more
core +2 more sources
Improving Structure-From-Motion and Rendering Quality for Thermal Image-Based 3D Gaussian Splatting
IEEE AccessNovel-view synthesis, which generates new views from images captured at multiple viewpoints, is widely applied in fields such as autonomous driving, robotic vision, architecture, and augmented reality.
Jinhoon Wang, Jusang Jeong, Junghyun Oh
doaj +1 more source
3D Reconstruction of Buildings Based on 3D Gaussian Splatting [PDF]
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information SciencesIn the current era of urban construction, smart city management, and digital twinning, three-dimensional reconstruction of urban buildings is particularly important.
Z. Cai +4 more
doaj +1 more source
Leveraging Part‐Based NeRF for Robot Self‐Modeling and Control
SmartBot, Volume 1, Issue 4, December 2025.A robot stands in front of a camera, striking a variety of distinct poses to provide diverse visual data. The camera then captures these images in sequence, storing every detail of the robot’s body position and movements. Using this visual input, the robot can gradually process and analyze the information, ultimately developing a basic sense of self ...
Kejun Hu +3 more
wiley +1 more source
Visual Simulation of Flow [PDF]
, 2010 We have adopted a numerical method from computational fluid dynamics, the Lattice Boltzmann Method (LBM), for real-time simulation and visualization of flow and amorphous phenomena, such as clouds, smoke, fire, haze, dust, radioactive plumes, and air ...
Kaufman, Arie, Zhao, Ye
core +1 more source
StyleMM: Stylized 3D Morphable Face Model via Text‐Driven Aligned Image Translation
Computer Graphics Forum, Volume 44, Issue 7, October 2025.Abstract We introduce StyleMM, a novel framework that can construct a stylized 3D Morphable Model (3DMM) based on user‐defined text descriptions specifying a target style. Building upon a pre‐trained mesh deformation network and a texture generator for original 3DMM‐based realistic human faces, our approach fine‐tunes these models using stylized facial
Seungmi Lee, Kwan Yun, Junyong Noh
wiley +1 more source
ClothingTwin: Reconstructing Inner and Outer Layers of Clothing Using 3D Gaussian Splatting
Computer Graphics Forum, Volume 44, Issue 7, October 2025.Abstract We introduce ClothingTwin, a novel end‐to‐end framework for reconstructing 3D digital twins of clothing that capture both the outer and inner fabric —without the need for manual mannequin removal. Traditional 2D “ghost mannequin” photography techniques remove the mannequin and composite partial inner textures to create images in which the ...
Munkyung Jung, Dohae Lee, In‐Kwon Lee
wiley +1 more source
Applied SciencesTo address the issues of parameter coupling and high computational demands in existing feed-forward Gaussian splatting methods, we propose Gaussian Patch-level Mixture-of-Experts Splatting (GaPMeS), a lightweight feed-forward 3D Gaussian reconstruction ...
Jinwen Liu, Wenchao Liu, Rui Guo
doaj +1 more source