SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.04805 · CVPR · 2023

X-Avatar: Expressive Human Avatars

Jie Song, Ka Shen, O. Hilliges, Chen Guo, Manuel Kaufmann, Julien Valentin, Juan Zarate

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

Figure 1. We propose X-Avatar, an animatible implicit human avatar model capable of capturing human body pose, hand pose, facial expressions, and appearance. X-Avatar can be created from input 3D scans (top row) or RGB-D images (bottom row) and displays highquality geometry as well as appearance under animation. X-Avatar captures facial expressions and hand gestures (right), making it the first implicit human avatar model to capture the richness of the human state in a unified model.

For agents

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

get_harvested_code_for_paper("2303.04805")
get_code_for_paper("2303.04805")
have("2303.04805")

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

curl https://syntology.ai/api/ran/2303.04805.json

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

[![Syntology run record](https://syntology.ai/api/ran/2303.04805.svg)](https://syntology.ai/paper/2303.04805)

Connect an agent — have() is free.