Unverified50% confidenceFactExact time
NeRF 通过神经网络从 2D 图像重建连续的 3D 场景表示，使虚拟漫游成为可能
1
Sources
50%
Confidence
Long-term
Relevance
7/14/2026
First Seen
Sources
Related Claims
VerifiedNeRF（神经辐射场）及其后继者Gaussian Splatting能够从2D图像重建可任意视角漫游的三维场景78% similarUnverified早期的NeRF（神经辐射场）方法需要多视角图片输入才能生成3D模型77% similarUnverifiedNeRF通过隐式神经网络将三维场景编码为连续体积密度与颜色函数，3D Gaussian Splatting以显式高斯椭球体表示场景几何且渲染速度更快71% similarUnverified3D坐标到2D像素坐标的转换流程为：世界坐标系→相机坐标系→裁剪坐标系→NDC→屏幕坐标系69% similarUnverifiedNeRF将场景表达为连续的隐式函数，通过体积渲染合成视图，重建质量高但推理速度较慢68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/509963API
curl https://kongchang.com/api/v1/knowledge/claims/509963MCP
get_claim(id=509963)