Unverified50% confidenceFactExact time
NeRF（Neural Radiance Fields）是一种隐式三维表示，能够从多张二维图像重建连续的三维场景，并支持任意视角的新视图合成
1
Sources
50%
Confidence
Long-term
Relevance
7/19/2026
First Seen
Sources
LeRobot 3D：为SO101机器人构建三维空间感知与操作能力
Related Claims
VerifiedNeRF (Neural Radiance Fields) and its successor Gaussian Splatting can reconstruct three-dimensional scenes that can be freely navigated from any viewpoint from 2D images.81% similarUnverifiedEarly NeRF (Neural Radiance Field) methods required multi-view image input to generate 3D models.73% similarUnverifiedNeRF由Ben Mildenhall等人于2020年提出，通过多层感知机隐式表示三维场景，可从稀疏照片重建逼真三维环境72% 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70% similarUnverified多视角扩散模型方法通过从单张或少量图片推断多视角一致性图像，再利用NeRF或3D Gaussian Splatting等方式重建三维结构，视觉质量占优但网格质量较差69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/563081API
curl https://kongchang.com/api/v1/knowledge/claims/563081MCP
get_claim(id=563081)