StdGEN++: A Comprehensive System for Semantic-Decomposed 3D Character Generation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918284079661056 |
|---|---|
| author | He, Yuze Zhou, Yanning Zhao, Wang Ye, Jingwen Wu, Zhongkai Yi, Ran Liu, Yong-Jin |
| author_facet | He, Yuze Zhou, Yanning Zhao, Wang Ye, Jingwen Wu, Zhongkai Yi, Ran Liu, Yong-Jin |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_07660 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | StdGEN++: A Comprehensive System for Semantic-Decomposed 3D Character Generation He, Yuze Zhou, Yanning Zhao, Wang Ye, Jingwen Wu, Zhongkai Yi, Ran Liu, Yong-Jin Computer Vision and Pattern Recognition 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. |
| title | StdGEN++: A Comprehensive System for Semantic-Decomposed 3D Character Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.07660 |