DreamCharacter-1: From 3D Generative Foundation Models to Product-Ready Character Generation
Abstract
We present DreamCharacter-1, a lightweight post-adaptation framework that calibrates pretrained 3D foundation models toward high-fidelity, production-ready 3D character generation. Building upon a 3D foundation backbone, our pipeline incorporates three task-oriented components: (1) geometry post-training, which enhances fine-grained surface details through geometric preference optimization; (2) texture post-training, which synthesizes high-resolution textures and refines the appearance of occluded regions; and (3) inference acceleration, which enables scalable deployment. Extensive quantitative and qualitative experiments demonstrate that DreamCharacter-1 produces visually compelling and structurally robust 3D character assets, consistently surpassing state-of-the-art character generation methods.
Keywords
Cite
@article{arxiv.2607.07817,
title = {DreamCharacter-1: From 3D Generative Foundation Models to Product-Ready Character Generation},
author = {Weizhe Liu and Yunjie Wu and Xiangqian Shu and Guangwei Wang and Xiangyu Xu and Peng Li and Yujie Li and Hengkai Guo},
journal= {arXiv preprint arXiv:2607.07817},
year = {2026}
}
Comments
Official Page: https://dreamcharacter-x.github.io/