Lune

CVPR2021顶会

ANR: Articulated Neural Rendering for Virtual Avatars

Amit Raj, Julian Tanke, James Hays, Minh Vo, Carsten Stoll, Christoph Lassner

2021年份
26顶会引用

摘要

3 Facebook Reality Labs 4 Epic Games Figure 1: We present Articulated Neural Rendering (ANR), a rendering framework capable of producing highly realistic avatars. Similar to Deferred Neural Rendering (DNR) [38], ANR uses neural networks to convert a latent texture on a coarse mesh (left) into an RGB image (right). Unlike DNR, which is ineffective when the mesh geometry is inaccurate or deforms during motion, ANR explicitly accounts for such geometric misalignment and pose-dependent deformation.

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 Paper26

问问它们各自怎么用它

它引用的顶会 Paper6

相关 Paper

黄昏的海面,两侧是细线勾勒的悬崖