Lune

CVPR2021Top-tier venue

ANR: Articulated Neural Rendering for Virtual Avatars

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

2021Year
26Top-tier citations

Abstract

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.

Ask about this paper

Your agent reads all of it.

Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.

Questions to start from

Your agent calls

Luneget_paper_fulltext

Ask in Lune

Free to start. No credit card required.

Cited by top-tier papers26

Ask how each one uses it

Builds on6

Related papers

Dusk over the sea between two cliffs drawn in fine vertical lines