Results 61 to 70 of about 3,037 (213)

Mesh Processing Non‐Meshes via Neural Displacement Fields

Computer Graphics Forum, EarlyView.
Abstract Mesh processing pipelines are mature, but adapting them to newer non‐mesh surface representations—which enable fast rendering with compact file size—requires costly meshing or transmitting bulky meshes, negating their core benefits for streaming applications.
Yuta Noma, Zhecheng Wang, Chenxi Liu, Karan Singh, Alec Jacobson   +4 more
wiley   +1 more source

HyperGS: Hyperspectral 3D Gaussian Splatting

2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
We introduce HyperGS, a novel framework for Hyperspectral Novel View Synthesis (HNVS), based on a new latent 3D Gaussian Splatting (3DGS) technique. Our approach enables simultaneous spatial and spectral renderings by encoding material properties from multi-view 3D hyperspectral datasets.
Thirgood, Christopher, Mendez, Oscar, Ling, Erin Chao, Storey, Jon, Hadfield, Simon   +4 more
openaire   +2 more sources

Improving Structure-From-Motion and Rendering Quality for Thermal Image-Based 3D Gaussian Splatting

IEEE Access
Novel-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 Gaussian Splatting Methods for Real-World Scenarios [PDF]

ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
3D Gaussian Splatting (3DGS) is an innovative solution for explicit point-based 3D representation where each point is represented as a Gaussian distribution. Using calibrated images and sparse point cloud for initialization, the scene is reconstructed by
I. Petrovska, B. Jutzi
doaj   +1 more source

Geometry-Based Next Frame Prediction from Monocular Video

, 2017
We consider the problem of next frame prediction from video input. A recurrent convolutional neural network is trained to predict depth from monocular video input, which, along with the current video image and the camera trajectory, can then be used to ...
Angelova, Anelia, Mahjourian, Reza, Wicke, Martin   +2 more
core   +1 more source

OUGS: Active View Selection via Object‐aware Uncertainty Estimation in 3DGS

Computer Graphics Forum, EarlyView.
Abstract Recent advances in 3D Gaussian Splatting (3DGS) have achieved state‐of‐the‐art results for novel view synthesis. However, efficiently capturing high‐fidelity reconstructions of specific objects within complex scenes remains a significant challenge.
Haiyi Li, Qi Chen, Denis Kalkofen, Hsiang‐Ting Chen   +3 more
wiley   +1 more source

Impact of Rain on 3D Reconstruction with Multi-View Stereo, Neural Radiance Fields and Gaussian Splatting [PDF]

ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Image-based 3D reconstruction uncovers many applications in documenting the geometry of the environment. Nonetheless, the assumption that images are captured in clear air rarely holds in real-world settings where adverse weather conditions are inevitable.
I. Petrovska, B. Jutzi
doaj   +1 more source

GaussianDiffusion: 3D Gaussian Splatting for Denoising Diffusion Probabilistic Models with Structured Noise

, 2023
Text-to-3D, known for its efficient generation methods and expansive creative potential, has garnered significant attention in the AIGC domain. However, the amalgamation of Nerf and 2D diffusion models frequently yields oversaturated images, posing ...
Li, Xinhai, Tseng, Kuo-Kun, Wang, Huaibin   +2 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, Huang Li, Joaquín Goñi, Joey A. Contreras, John D. West, Li Shen, null null, Olaf Sporns, Shannon L. Risacher, Shiaofen Fang, Yang Wang   +10 more
core   +2 more sources

LeafFit: Plant Assets Creation from 3D Gaussian Splatting

Computer Graphics Forum, EarlyView.
Abstract We propose LeafFit, a pipeline that converts 3D Gaussian Splatting (3DGS) of individual plants into editable, instanced mesh assets. While 3DGS faithfully captures complex foliage, its high memory footprint and lack of mesh topology make it incompatible with traditional game production workflows. We address this by leveraging the repetition of
Chang Luo, Nobuyuki Umetani
wiley   +1 more source