Recent advancements in Gaussian Splatting (3DGS) have introduced various modifications to the original kernel, resulting in significant performance improvements. However, many of these kernel changes are incompatible with existing datasets optimized for the original Gaussian kernel, presenting a challenge for widespread adoption. In this work, we address this challenge by proposing an alternative kernel that maintains compatibility with existing datasets while improving computational efficiency. Specifically, we replace the original exponential kernel with a polynomial approximation combined with a ReLU function. This modification allows for more aggressive culling of Gaussians, leading to enhanced performance across different 3DGS implementations. Our results show a notable performance improvement of 4 to 15% with negligible impact on image quality. We also provide a detailed mathematical analysis of the new kernel and discuss its potential benefits for 3DGS implementations on NPU hardware.
Isotropic Gaussian Splatting for Real-Time Radiance Field Rendering
College of Electronics and Information Engineering, Shenzhen University(深圳大学电子与信息工程学院);Guangdong Key Laboratory of Intelligent Information Processing(广东省智能信息处理重点实验室);Adobe Inc.(奥多比公司);School of Biomedical Engineering, Shenzhen University(深圳大学生物医学工程学院)
4DRGS: 4D Radiative Gaussian Splatting for Efficient 3D Vessel Reconstruction from Sparse-View Dynamic DSA Images
State Key Laboratory of Advanced Medical Materials and Devices, ShanghaiTech University(上海科技大学先进医用材料与器件国家重点实验室);School of Computing, Australian National University(澳大利亚国立大学计算学院);School of Computer Science, Wuhan University(武汉大学计算机学院)
SuperGaussians: Enhancing Gaussian Splatting Using Primitives with Spatially Varying Colors
The University of Hong Kong(香港大学);Shenzhen Graduate School of Peking University(北京大学深圳研究生院);Nanyang Technological University(南洋理工大学);Hong Kong University of Science and Technology(香港科技大学);Macau University of Science and Technology(澳门科技大学);Shandong University(山东大学);Texas A&M University(德克萨斯农工大学)
Forecasting as Rendering: A 2D Gaussian Splatting Framework for Time Series Forecasting
Tsinghua Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院);College of Computer Science and Software Engineering, Shenzhen University(深圳大学计算机科学与软件工程学院)
SolidGS: Consolidating Gaussian Surfel Splatting for Sparse-View Surface Reconstruction
Texas A&M University(德克萨斯农工大学);OPPO US Research Center(OPPO美国研究中心);Nanyang Technological University(南洋理工大学);Hong Kong University of Science and Technology(香港科技大学);The University of Hong Kong(香港大学)
GaussianSR: High Fidelity 2D Gaussian Splatting for Arbitrary-Scale Image Super-Resolution
The Hong Kong Polytechnic University(香港理工大学);OPPO Research Institute(OPPO研究院);Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院);The Chinese University of Hong Kong(香港中文大学);Peking University(北京大学)
Reprojection-Guided 3D Gaussian Splatting Diffusion for Weakly Supervised Single-Image Normal Estimation
School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China(江南大学人工智能与计算机科学学院,中国无锡);School of Data Science, Lingnan University, Hong Kong, China(岭南大学数据科学学院,中国香港)
ExtrinSplat: Decoupling Geometry and Semantics for Open-Vocabulary Understanding in 3D Gaussian Splatting
Guangdong Provincial Key Laboratory of Ultra High Definition Immersive Media Technology, Shenzhen Graduate School, Peking University(广东省超高清沉浸式媒体技术重点实验室,北京大学深圳研究生院);School of Computer Science and Technology, Tianjin University(天津大学计算机科学与技术学院);Guangdong Bohua UHD Innovation Center Co., Ltd.(广东博华超高清创新中心有限公司)
BRF-GS: Hyperspectral Bidirectional Reflectance Factor Modeling and Image Generation Based on 3D Gaussian Splatting
Aerospace Information Research Institute, Chinese Academy of Sciences(中国科学院空天信息创新研究院);International Research Center of Big Data for Sustainable Development Goals(国际可持续发展大数据研究中心);University of Chinese Academy of Sciences(中国科学院大学)