Results 111 to 120 of about 429 (147)

Intraoperative 3D reconstruction from sparse arbitrarily posed real X-rays

Scientific Reports
Spine surgery is a high-risk intervention demanding precise execution, often supported by image-based navigation systems. Recently, supervised learning approaches have gained attention for reconstructing 3D spinal anatomy from sparse fluoroscopic data ...
Sascha Jecklin, Aidana Massalimova, Ruyi Zha, Lilian Calvet, Christoph J. Laux, Mazda Farshad, Philipp Fürnstahl   +6 more
doaj   +1 more source

3D Gaussian Splatting with Deferred Reflection

Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers 24
The advent of neural and Gaussian-based radiance field methods have achieved great success in the field of novel view synthesis. However, specular reflection remains non-trivial, as the high frequency radiance field is notoriously difficult to fit stably and accurately. We present a deferred shading method to effectively render specular reflection with
Keyang Ye, Qiming Hou, Kun Zhou 0001
openaire   +2 more sources

3D reconstruction for unconstrained image collections using Gaussian Splatting with foundation model

Geo-spatial Information Science
Achieving high-quality rendering with Gaussian Splatting for unconstrained image collections is critical for advancing 3D reconstruction. Currently, the methods using a single multi-layer perceptron and convolutional neural network to predict distractors
Shuowen Huang, Qingwu Hu, Pengcheng Zhao, Mingyao Ai, Xujie Zhang, Wenwu Ou, Linze Li   +6 more
doaj   +1 more source

Gaussian splatting holography

In-line holography offers high space-bandwidth product imaging with a simplified lens-free optical system. However, in-line holographic reconstruction is troubled by twin images arising from the Hermitian symmetry of complex fields. Twin images disrupt the reconstruction in solving the ill-posed phase retrieval problem.
Zhang, Shuhe, Cao, Liangcai
openaire   +2 more sources

FHGS: Feature-Homogenized Gaussian Splatting

CoRR
Scene understanding based on 3D Gaussian Splatting (3DGS) has recently achieved notable advances. Although 3DGS related methods have efficient rendering capabilities, they fail to address the inherent contradiction between the anisotropic color representation of gaussian primitives and the isotropic requirements of semantic features, leading to ...
Guangya Duan, Benyun Zhao, Mingqiao Han, Yijun Huang, Ben M. Chen   +4 more
openaire   +2 more sources

Cut-and-Splat: Leveraging Gaussian Splatting for Synthetic Data Generation

Generating synthetic images is a useful method for cheaply obtaining labeled data for training computer vision models. However, obtaining accurate 3D models of relevant objects is necessary, and the resulting images often have a gap in realism due to challenges in simulating lighting effects and camera artifacts.
Bram Vanherle, Brent Zoomers, Jeroen Put, Frank Van Reeth, Nick Michiels   +4 more
openaire   +3 more sources

3D Gaussian Splatting in Robotics: A Survey

CoRR
Dense 3D representations of the environment have been a long-term goal in the robotics field. While previous Neural Radiance Fields (NeRF) representation have been prevalent for its implicit, coordinate-based model, the recent emergence of 3D Gaussian Splatting (3DGS) has demonstrated remarkable potential in its explicit radiance field representation ...
Zhu, Siting, Wang, Guangming, Kong, Xin, Kong, Dezhi, Wang, Hesheng   +4 more
openaire   +2 more sources

Uncertainty-Guided Zero-Watermarking for 3D Gaussian Splatting

Applied Sciences
3D Gaussian Splatting (3DGS) has emerged as a cornerstone technique for 3D asset acquisition. However, existing copyright protection methods for 3DGS predominantly rely on embedding watermarks directly into Gaussian primitives, which inevitably degrades ...
Xiaoqiang Zhu, Kehan Long
doaj   +1 more source

Integration of 3D Gaussian Splatting and Neural Radiance Fields in Virtual Reality Fire Fighting

Remote Sensing
Neural radiance fields (NeRFs) and 3D Gaussian splatting have emerged as promising 3D reconstruction techniques recently. However, their application in virtual reality (VR), particularly in firefighting training, remains underexplored.
Haojie Lian, Kangle Liu, Ruochen Cao, Ziheng Fei, Xin Wen, Leilei Chen   +5 more
doaj   +1 more source

Text-to-3D using Gaussian Splatting

2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
To appear at CVPR 2024. Project page: https://gsgen3d.github.io.
Zilong Chen, Feng Wang 0034, Yikai Wang 0001, Huaping Liu 0001   +3 more
openaire   +2 more sources