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

2026-05-23

AI Summary

This work addresses the high cost of manual modeling and rigging, which hinders the scalable acquisition of controllable 3D assets required by graphics, embodied intelligence, and interactive content creation. Inspired by biological structures, we propose a unified rib-spine representation that generalizes fishbone-like skeletons for the first time, enabling automatic construction of parameterized deformation rigs from a single mesh without category-specific priors. Our method integrates an adaptive heat-equation-based geodesic scalar field, isocontour-based rib extraction, geometry-aware spine computation, and Gaussian-weighted skinning. Leveraging Hunyuan3D, we introduce Fishbone-136K, a large-scale dataset of rigged 3D models. The framework supports real-time local and global deformations, reduced-dimensional dynamics simulation, and keyframe animation, demonstrating its efficiency and versatility in controllable generation, robot morphology augmentation, and agent-driven content creation.

Abstract

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.

Problem

• controllable 3D assets
• shape deformation
• parametric editing
• mesh variation
• 3D content creation

Innovation

• Fishbone representation
• controllable 3D deformation
• rib-spine structure
• geometry-aware parametric modeling
• reduced-space dynamics