BriefGPT.xyz
May, 2024
训练中显现的潜在内在特征
Latent Intrinsics Emerge from Training to Relight
HTML
PDF
Xiao Zhang, William Gao, Seemandhar Jain, Michael Maire, David. A. Forsyth...
TL;DR
图像重照是通过改变光照条件展示源图像场景在不同光照条件下的效果。本文介绍了一种完全基于数据驱动的重照方法，其中光照条件和内在特征都被表示为潜在变量。该方法在真实场景的重照上达到了最先进的水平，使用了标准度量评估，同时发现可以通过潜在内在特征恢复颜色，并且恢复的颜色与最先进的方法相竞争。
Abstract
image relighting
is the task of showing what a scene from a source image would look like if illuminated differently.
inverse graphics
schemes recover an explicit representation of geometry and a set of chosen int
→