SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2104.05988 · ICCV · 2021

VariTex: Variational Neural Face Textures

Otmar Hilliges, Thabo Beeler, Abhimitra Meka, Marcel Bühler, Gengyan Li

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

https://mcbuehler.github.io/VariTex Figure 1. VariTex generalizes person-specific neural textures to variational textures. This allows to control both pose and expressions via explicit 3D geometries (Fig. 3) and to sample novel identities (Fig. 5). Our method generates images under fine head pose and expression control, while maintaining geometric consistency over a large range of these parameters (Fig. 4 and Tbl. 2).

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2104.05988")
get_code_for_paper("2104.05988")
have("2104.05988")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2104.05988.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2104.05988.svg)](https://syntology.ai/paper/2104.05988)

Connect an agent — have() is free.