Results 91 to 100 of about 3,037 (213)

Adaptive Deletion of Gaussian Ellipsoids in 3D Gaussian Splatting

Mathematics
As a leading method for Novel View Synthesis (NVS), 3D Gaussian Splatting (3DGS) faces limitations. Fixed thresholds governing Gaussian scale and opacity lead to over-reconstruction or under-reconstruction, while the linear penalty used for handling ...
Fei Zhang, Yinghui Wang, Bo Yi, Jiaxin Ma   +3 more
doaj   +1 more source

Progressive refinement rendering of implicit surfaces [PDF]

, 2007
The visualisation of implicit surfaces can be an inefficient task when such surfaces are complex and highly detailed. Visualising a surface by first converting it to a polygon mesh may lead to an excessive polygon count.
Amanatides, Bergman, Blinn, Bloomenthal, Cohen, de Figueiredo, Duff, Farrugia, Gamito, Genetti, Guo, Hanrahan, Hart, Hart, Kalra, Laur, Lewis, Lippert, Lorensen, Maillot, Manuel N. Gamito, Mitchell, Morse, Painter, Perlin, Saupe, Steve C. Maddock, Turk, Velho, Whitted, Witkin, Wolfe, Woodwark, Worley, Worley   +34 more
core   +2 more sources

Optimized Minimal 3D Gaussian Splatting

Project page: https://maincold2.github.io/omg/
Lee, Joo Chan, Ko, Jong Hwan, Park, Eunbyung   +2 more
openaire   +2 more sources

PlantGaussian: Exploring 3D Gaussian splatting for cross-time, cross-scene, and realistic 3D plant visualization and beyond

Crop Journal
Observing plants across time and diverse scenes is critical in uncovering plant growth patterns. Classic methods often struggle to observe or measure plants against complex backgrounds and at different growth stages.
Peng Shen, Xueyao Jing, Wenzhe Deng, Hanyue Jia, Tingting Wu   +4 more
doaj   +1 more source

WildGaussians: 3D Gaussian Splatting In the Wild

Advances in Neural Information Processing Systems 37
NeurIPS 2024; Project page: https://wild-gaussians.github.io/
Kulhanek, Jonas, Peng, Songyou, Kukelova, Zuzana, Pollefeys, Marc, Sattler, Torsten   +4 more
openaire   +3 more sources

CDGS: Confidence-Aware Depth Regularization for 3D Gaussian Splatting [PDF]

The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
3D Gaussian Splatting (3DGS) has shown significant advantages in novel view synthesis (NVS), particularly in achieving high rendering speeds and high-quality results. However, its geometric accuracy in 3D reconstruction remains limited due to the lack of
Q. Zhang, O. Wysocki, S. Urban, B. Jutzi
doaj   +1 more source

ThermalGaussian: Thermal 3D Gaussian Splatting

Thermography is especially valuable for the military and other users of surveillance cameras. Some recent methods based on Neural Radiance Fields (NeRF) are proposed to reconstruct the thermal scenes in 3D from a set of thermal and RGB images. However, unlike NeRF, 3D Gaussian splatting (3DGS) prevails due to its rapid training and real-time rendering.
Lu, Rongfeng, Chen, Hangyu, Zhu, Zunjie, Qin, Yuhang, Lu, Ming, Zhang, Le, Yan, Chenggang, Xue, Anke   +7 more
openaire   +2 more sources

TreeDGS: Aerial Gaussian Splatting for Distant DBH Measurement

Remote Sensing
Aerial remote sensing efficiently surveys large areas, but accurate direct object-level measurement remains difficult in complex natural scenes. Advancements in 3D computer vision, particularly radiance field representations such as NeRF and 3D Gaussian ...
Belal Shaheen, Minh-Hieu Nguyen, Bach-Thuan Bui, Shubham, Tim Wu, Michael Fairley, Matthew Zane, Michael Wu, James Tompkin   +8 more
doaj   +1 more source

SurfelWarp: Efficient Non-Volumetric Single View Dynamic Reconstruction

, 2019
We contribute a dense SLAM system that takes a live stream of depth images as input and reconstructs non-rigid deforming scenes in real time, without templates or prior models.
Gao, Wei, Tedrake, Russ
core   +1 more source

3D Vision-Language Gaussian Splatting

Recent advancements in 3D reconstruction methods and vision-language models have propelled the development of multi-modal 3D scene understanding, which has vital applications in robotics, autonomous driving, and virtual/augmented reality. However, current multi-modal scene understanding approaches have naively embedded semantic representations into 3D ...
Peng, Qucheng, Planche, Benjamin, Gao, Zhongpai, Zheng, Meng, Choudhuri, Anwesa, Chen, Terrence, Chen, Chen, Wu, Ziyan   +7 more
openaire   +2 more sources