StdGEN++: 一种用于语义分解3D人物生成的综合性系统
StdGEN++: A Comprehensive System for Semantic-Decomposed 3D Character Generation
AI总结:
StdGEN++是一种基于双分支语义感知模型的综合性系统,通过语义分解和高效生成技术,实现高保真3D人物生成,适用于自动化角色资产生产。
摘要:
我们介绍了StdGEN++,一种新型且全面的系统,用于从多种输入中生成高保真的语义分解3D人物。现有的3D生成方法往往产生整体网格,缺乏游戏和动画工业管线所需结构灵活性。为解决这一缺口,StdGEN++基于双分支语义感知大重建模型(Dual-Branch S-LRM),以前馈方式联合重建几何体、颜色和各组件语义。为了实现生产级保真度,我们引入了一种新的语义表面提取形式,与混合隐式场兼容。该机制通过粗到细的提案方案加速,显著减少了内存占用并实现了高分辨率网格生成。此外,我们提出了一种基于视频扩散的纹理分解模块,将外观分解为可编辑的层(例如,分离虹膜和皮肤),解决了面部区域的语义混淆。实验表明,StdGEN++在几何精度和语义解耦方面显著优于现有方法。关键的是,所得到的结构独立性解锁了高级下游能力,包括非破坏性编辑、符合物理的动画和目光追踪,使其成为自动化人物资产生产的稳健解决方案。
英文摘要:
We present StdGEN++, a novel and comprehensive system for generating high-fidelity, semantically decomposed 3D characters from diverse inputs. Existing 3D generative methods often produce monolithic meshes that lack the structural flexibility required by industrial pipelines in gaming and animation. Addressing this gap, StdGEN++ is built upon a Dual-branch Semantic-aware Large Reconstruction Model (Dual-Branch S-LRM), which jointly reconstructs geometry, color, and per-component semantics in a feed-forward manner. To achieve production-level fidelity, we introduce a novel semantic surface extraction formalism compatible with hybrid implicit fields. This mechanism is accelerated by a coarse-to-fine proposal scheme, which significantly reduces memory footprint and enables high-resolution mesh generation. Furthermore, we propose a video-diffusion-based texture decomposition module that disentangles appearance into editable layers (e.g., separated iris and skin), resolving semantic confusion in facial regions. Experiments demonstrate that StdGEN++ achieves state-of-the-art performance, significantly outperforming existing methods in geometric accuracy and semantic disentanglement. Crucially, the resulting structural independence unlocks advanced downstream capabilities, including non-destructive editing, physics-compliant animation, and gaze tracking, making it a robust solution for automated character asset production.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。