Lune

CVPR2024顶会

High-Quality Facial Geometry and Appearance Capture at Home

Yuxuan Han, Junfeng Lyu, Feng Xu

2024年份
6顶会引用

摘要

Data Capture Recon. Geometry and Reflectance a single co-located sequence normal mesh diffuse albedo specular albedo roughness Relighting high-quality renderings with plausible eyes' specularities Figure 1. We propose a novel method for high-quality face capture, featuring a low-cost and easy-to-use capture setup and the capability to model the complete face with skin, mouth interior, hair, and eyes. Our method takes a single co-located smartphone flashlight sequence captured in a dim room (e.g. rooms with curtains or at night) as input. It reconstructs relightable 3D face assets from the recorded data. These can be used by common graphics software like Blender to create photo-realistic renderings in new environments.

问问这篇 Paper

智能体会读完全文。

Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。

可以从这些问题问起

智能体调用

Luneget_paper_fulltext

在 Lune 里问

免费开始,无需绑卡

引用它的顶会 Paper6

问问它们各自怎么用它

它引用的顶会 Paper31

相关 Paper

黄昏的海面,两侧是细线勾勒的悬崖