arXiv:2605.24805cs.CV2026-05被引 1

用脊骨与肋骨结构实现3D模型的实时可控变形。

Fishbone: From One 3D Asset to a Million Controllable Edits

论文配图:Fishbone: From One 3D Asset to a Million Controllable Edits
图 1 · 摘自论文原文
  • 通过几何热法提取等高线作为肋骨,构建骨架控制全局形态。
  • 支持实时变形、简化动力学模拟与关键帧动画,提升编辑效率。
  • 适用于机器人学习数据增强、交互式建模与智能生成任务。

大规模可控制3D资产对计算机图形学、具身AI、机器人及互动内容创作至关重要,但手工建模与绑定成本高昂。形状变形可从现有网格生成变体,但现有数据驱动方法依赖稀疏用户输入,参数化编辑框架需手动设计控制结构并针对类别配置。受自然生物启发——中央脊柱控制整体形态,横截面肋骨调控局部变化——我们提出Fishbone,一种统一的肋-脊表示框架,支持参数化网格变形、降维动力学与动画。给定输入网格,Fishbone采用自适应热法计算测地标量场,提取等高线作为横截面肋骨,通过肋骨中心构建平滑的几何感知脊柱,并利用高斯加权皮肤化将表面顶点关联至邻近的肋骨与脊柱结构。该表示支持实时且可预测的变形:肋骨控制厚度、方向与横截面变化等局部特征,脊柱控制整体弯曲、扭转与拉伸。同一结构亦支持降维模拟与关键帧动画。我们进一步通过在Hunyuan3D基础上添加肋-脊结构构建了Fishbone-136K数据集,并在可控3D生成、基于变形的数据增强(用于机器人学习)、交互式网格编辑与代理生成等任务中验证其有效性。实验表明该框架具备高效性、通用性与强大实用性。

原文摘要 · Abstract (English)

Large-scale controllable 3D assets are critical for computer graphics, embodied AI, robotics, and interactive content creation, yet creating diverse 3D assets remains challenging due to the high cost of manual modeling and rigging. Shape deformation offers a natural way to generate variations from existing meshes, but existing data-driven methods often rely on sparse user inputs, while parametric editing frameworks require manually designed control structures and category-specific configurations. Inspired by natural creatures, where a central spine governs global shape and cross-sectional ribs control local variation, we introduce Fishbone, a unified rib-spine representation for general shapes that supports controllable parametric mesh deformation, reduced-space dynamics, and animation. Given an input mesh, Fishbone computes a geodesic scalar field with an adaptive heat method, extracts iso-contours as cross-sectional ribs, constructs a smooth geometry-aware spine through rib centers, and associates surface vertices with nearby rib and spine structures using Gaussian-weighted skinning. The resulting representation enables real-time and predictable deformation: ribs control local profiles such as thickness, orientation, and cross-sectional variation, while the spine controls global bending, twisting, and stretching. The same structure also supports reduced-space simulation and keyframe animation. We further construct Fishbone-136K by augmenting Hunyuan3D with rib-spine structures, and demonstrate applications in controllable 3D generation, deformation-based data augmentation for robot learning, interactive mesh editing, and agentic generation. Experiments demonstrate the effectiveness, efficiency, and versatility of the proposed framework.

3D生成参数化变形骨骼系统机器人学习

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。