轻量级框架让3D角色生成更逼真、可量产。
DreamCharacter-1: From 3D Generative Foundation Models to Product-Ready Character Generation
- 分三步优化：几何细节、纹理清晰度、推理速度
- 生成角色视觉逼真，结构稳定，超越现有方法
- 适合游戏影视行业快速产出高质量3D角色
我们提出DreamCharacter-1，一种轻量级后适配框架，用于将预训练3D基础模型校准为高保真、可投产的3D角色生成系统。基于3D基础模型骨干网络，该流程包含三个任务导向组件：(1) 几何后训练，通过几何偏好优化增强细微表面细节；(2) 纹理后训练，合成高分辨率纹理并修复遮挡区域外观；(3) 推理加速，实现可扩展部署。大量定量与定性实验表明，DreamCharacter-1生成的3D角色资产视觉上引人入胜且结构稳健，持续优于当前最优角色生成方法。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。