BriefGPT.xyz
Nov, 2019
利用可微球追踪渲染深度隐式有符号距离函数
DIST: Rendering Deep Implicit Signed Distance Function with Differentiable Sphere Tracing
HTML
PDF
Shaohui Liu, Yinda Zhang, Songyou Peng, Boxin Shi, Marc Pollefeys...
TL;DR
提出了一种可微球追踪算法,可以将隐式有符号距离函数的深度学习方法与逆向图形方法联系起来。该渲染方法可以高效地重建不同类型的 3D 形状,具有优秀的泛化能力和稳健性。
Abstract
We propose a
differentiable sphere tracing algorithm
to bridge the gap between inverse graphics methods and the recently proposed
deep learning
based
→