AgileAvatar: Stylized 3D Avatar Creation via Cascaded Domain Bridging

11/15/2022
by   Shen Sang, et al.
0

Stylized 3D avatars have become increasingly prominent in our modern life. Creating these avatars manually usually involves laborious selection and adjustment of continuous and discrete parameters and is time-consuming for average users. Self-supervised approaches to automatically create 3D avatars from user selfies promise high quality with little annotation cost but fall short in application to stylized avatars due to a large style domain gap. We propose a novel self-supervised learning framework to create high-quality stylized 3D avatars with a mix of continuous and discrete parameters. Our cascaded domain bridging framework first leverages a modified portrait stylization approach to translate input selfies into stylized avatar renderings as the targets for desired 3D avatars. Next, we find the best parameters of the avatars to match the stylized avatar renderings through a differentiable imitator we train to mimic the avatar graphics engine. To ensure we can effectively optimize the discrete parameters, we adopt a cascaded relaxation-and-search pipeline. We use a human preference study to evaluate how well our method preserves user identity compared to previous work as well as manual creation. Our results achieve much higher preference scores than previous work and close to those of manual creation. We also provide an ablation study to justify the design choices in our pipeline.

READ FULL TEXT

page 1

page 3

page 4

page 5

page 6

page 7

page 8

research
09/14/2020

Cascade Network for Self-Supervised Monocular Depth Estimation

It is a classical compute vision problem to obtain real scene depth maps...
research
08/17/2020

Neutral Face Game Character Auto-Creation via PokerFace-GAN

Game character customization is one of the core features of many recent ...
research
12/14/2020

Continuous Curve Textures

Repetitive patterns are ubiquitous in natural and human-made objects, an...
research
12/25/2020

A Cascaded Residual UNET for Fully Automated Segmentation of Prostate and Peripheral Zone in T2-weighted 3D Fast Spin Echo Images

Multi-parametric MR images have been shown to be effective in the non-in...
research
03/02/2023

Zero-Shot Text-to-Parameter Translation for Game Character Auto-Creation

Recent popular Role-Playing Games (RPGs) saw the great success of charac...
research
03/26/2021

Modeling the Compatibility of Stem Tracks to Generate Music Mashups

A music mashup combines audio elements from two or more songs to create ...
research
08/17/2020

Fast and Robust Face-to-Parameter Translation for Game Character Auto-Creation

With the rapid development of Role-Playing Games (RPGs), players are now...

Please sign up or login with your details

Forgot password? Click here to reset