Make-A-Character 2: Animatable 3D Character Generation From a Single Image

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Liu, Lin, Wang, Yutong, Chen, Jiahao, Li, Jianfang, Xue, Tangli, Li, Longlong, Ren, Jianqiang, Bo, Liefeng
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912189106880512
author Liu, Lin
Wang, Yutong
Chen, Jiahao
Li, Jianfang
Xue, Tangli
Li, Longlong
Ren, Jianqiang
Bo, Liefeng
author_facet Liu, Lin
Wang, Yutong
Chen, Jiahao
Li, Jianfang
Xue, Tangli
Li, Longlong
Ren, Jianqiang
Bo, Liefeng
contents This report introduces Make-A-Character 2, an advanced system for generating high-quality 3D characters from single portrait photographs, ideal for game development and digital human applications. Make-A-Character 2 builds upon its predecessor by incorporating several significant improvements for image-based head generation. We utilize the IC-Light method to correct non-ideal illumination in input photos and apply neural network-based color correction to harmonize skin tones between the photos and game engine renders. We also employ the Hierarchical Representation Network to capture high-frequency facial structures and conduct adaptive skeleton calibration for accurate and expressive facial animations. The entire image-to-3D-character generation process takes less than 2 minutes. Furthermore, we leverage transformer architecture to generate co-speech facial and gesture actions, enabling real-time conversation with the generated character. These technologies have been integrated into our conversational AI avatar products.
format Preprint
id arxiv_https___arxiv_org_abs_2501_07870
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Make-A-Character 2: Animatable 3D Character Generation From a Single Image
Liu, Lin
Wang, Yutong
Chen, Jiahao
Li, Jianfang
Xue, Tangli
Li, Longlong
Ren, Jianqiang
Bo, Liefeng
Computer Vision and Pattern Recognition
This report introduces Make-A-Character 2, an advanced system for generating high-quality 3D characters from single portrait photographs, ideal for game development and digital human applications. Make-A-Character 2 builds upon its predecessor by incorporating several significant improvements for image-based head generation. We utilize the IC-Light method to correct non-ideal illumination in input photos and apply neural network-based color correction to harmonize skin tones between the photos and game engine renders. We also employ the Hierarchical Representation Network to capture high-frequency facial structures and conduct adaptive skeleton calibration for accurate and expressive facial animations. The entire image-to-3D-character generation process takes less than 2 minutes. Furthermore, we leverage transformer architecture to generate co-speech facial and gesture actions, enabling real-time conversation with the generated character. These technologies have been integrated into our conversational AI avatar products.
title Make-A-Character 2: Animatable 3D Character Generation From a Single Image
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2501.07870