光辉
渲染(计算机图形)
计算机科学
视图合成
人工智能
可微函数
计算机视觉
卷积神经网络
计算机图形学(图像)
基于图像的建模与绘制
体绘制
函数表示法
人工神经网络
代表(政治)
集合(抽象数据类型)
全局照明
地理
数学
对象(语法)
遥感
政治
政治学
数学分析
程序设计语言
法学
作者
Ben Mildenhall,Pratul P. Srinivasan,Matthew Tancik,Jonathan T. Barron,Ravi Ramamoorthi,Ren Ng
标识
DOI:10.1007/978-3-030-58452-8_24
摘要
We present a method that achieves state-of-the-art results for synthesizing novel views of complex scenes by optimizing an underlying continuous volumetric scene function using a sparse set of input views. Our algorithm represents a scene using a fully-connected (non-convolutional) deep network, whose input is a single continuous 5D coordinate (spatial location (x, y, z) and viewing direction $$(\theta ,\phi )$$ ) and whose output is the volume density and view-dependent emitted radiance at that spatial location. We synthesize views by querying 5D coordinates along camera rays and use classic volume rendering techniques to project the output colors and densities into an image. Because volume rendering is naturally differentiable, the only input required to optimize our representation is a set of images with known camera poses. We describe how to effectively optimize neural radiance fields to render photorealistic novel views of scenes with complicated geometry and appearance, and demonstrate results that outperform prior work on neural rendering and view synthesis. View synthesis results are best viewed as videos, so we urge readers to view our supplementary video for convincing comparisons.
科研通智能强力驱动
Strongly Powered by AbleSci AI