Unverified50% confidenceFactExact time
3D Gaussian Splatting由Inria和Max Planck研究所于2023年提出，采用显式表示，通过可微分光栅化实现实时渲染（通常可达100+ FPS），训练时间缩短到分钟级别
1
Sources
50%
Confidence
Long-term
Relevance
8/15/2026
First Seen
Sources
虚拟篮球场AI训练指南：3D生成、物理仿真与生成式AI路径详解
Related Claims
Unverified3D Gaussian Splatting elevated neural rendering speed to real-time levels in 2023.78% similarVerified3D Gaussian Splatting (3DGS) was proposed in 2023 by the French INRIA team, achieving rendering speeds dozens of times faster than NeRF while maintaining comparable image quality.74% similarUnverified基于3D Gaussian Splatting的方法以显式高斯椭球集合表示三维场景，实现了远超NeRF的渲染速度70% similarUnverifiedNeRF（Neural Radiance Field）于2020年提出，通过隐式神经表示编码三维场景，可高质量合成任意视角图像，但推理耗时达数十秒至数分钟61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/753249API
curl https://kongchang.com/api/v1/knowledge/claims/753249MCP
get_claim(id=753249)