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

• URL: http://arxiv.org/abs/2605.24805v1
• Date: Sun, 24 May 2026 01:38:43 GMT
• Title: Fishbone: From One 3D Asset to a Million Controllable Edits
• Abstract summary: Fishbone is a unified rib-spine representation for general shapes that supports controllable parametric mesh, reduced-space dynamics, and animation.<n> ribs control local profiles such as thickness, orientation, and cross-sectional variation, while the spine controls global bending, twisting, and stretching.<n>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.
• Score: 26.573828978137104
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• ViP-Rig: Visual-Prompted Controllable Rigging [66.07397903377584]
  ViP-Rig is a visual-prompted framework that supports both prompt-first rigging and result-guided editing.<n>We show that ViP-Rig more accurately recovers target skeletons and skinning weights than geometry-conditioned baselines under prompt-guided evaluation.
  arXiv  Detail & Related papers  (2026-07-30T10:26:37Z)
• Zero Shot Deformation Reconstruction for Soft Robots Using a Flexible Sensor Array and Cage Based 3D Gaussian Modeling [13.363052557818968]
  zero-shot deformation reconstruction is defined as the ability to infer object-wide deformations on unseen soft robots without collecting deformation data or performing any retraining during deployment.<n>The proposed framework integrates a flexible piezoresistive sensor array with a geometry-aware, cage-based 3D Gaussian deformation model.<n>It achieves 0.67 IoU, 0.65 SSIM, and 3.48 mm Chamfer distance, demonstrating strong zero-shot generalization through explicit coupling of tactile sensing and structured geometric deformation.
  arXiv  Detail & Related papers  (2026-03-20T00:56:39Z)
• Adaptive Scaling with Geometric and Visual Continuity of completed 3D objects [0.0]
  We introduce a part-aware scaling framework that transforms static completed SDFs into structurally coherent objects.<n>Our method overcomes the inherent rigidity of completed SDFs and is visually more appealing than global and naive selective scaling.
  arXiv  Detail & Related papers  (2026-02-13T13:05:54Z)
• Stroke3D: Lifting 2D strokes into rigged 3D model via latent diffusion models [53.32092058519587]
  Stroke3D is a novel framework that directly generates rigged meshes from user inputs: 2D drawn strokes and a descriptive text prompt.<n>To the best of our knowledge, our work is the first to generate rigged 3D meshes conditioned on user-drawn 2D strokes.
  arXiv  Detail & Related papers  (2026-02-10T12:17:00Z)
• Enhancing non-Rigid 3D Model Deformations Using Mesh-based Gaussian Splatting [0.0]
  We propose a novel framework that enhances non-rigid 3D model deformations by bridging mesh representations with 3D Gaussian splatting.<n>This work paves the way for more flexible 3D content-creation in applications spanning virtual reality, character animation, and interactive design.
  arXiv  Detail & Related papers  (2025-07-09T16:26:04Z)
• RigAnything: Template-Free Autoregressive Rigging for Diverse 3D Assets [44.655049022141384]
  We present RigAnything, a novel autoregressive transformer-based model.<n>It makes 3D assets rig-ready by probabilistically generating joints and skeleton topologies and assigning skinning weights in a template-free manner.<n>It demonstrates state-of-the-art performance across diverse object types, including humanoids, quadrupeds, marine creatures, insects, and many more.
  arXiv  Detail & Related papers  (2025-02-13T18:59:13Z)
• Learning Modulated Transformation in GANs [69.95217723100413]
  We equip the generator in generative adversarial networks (GANs) with a plug-and-play module, termed as modulated transformation module (MTM) MTM predicts spatial offsets under the control of latent codes, based on which the convolution operation can be applied at variable locations. It is noteworthy that towards human generation on the challenging TaiChi dataset, we improve the FID of StyleGAN3 from 21.36 to 13.60, demonstrating the efficacy of learning modulated geometry transformation.
  arXiv  Detail & Related papers  (2023-08-29T17:51:22Z)
• MoDA: Modeling Deformable 3D Objects from Casual Videos [84.29654142118018]
  We propose neural dual quaternion blend skinning (NeuDBS) to achieve 3D point deformation without skin-collapsing artifacts. In the endeavor to register 2D pixels across different frames, we establish a correspondence between canonical feature embeddings that encodes 3D points within the canonical space. Our approach can reconstruct 3D models for humans and animals with better qualitative and quantitative performance than state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-04-17T13:49:04Z)
• Geometry-Contrastive Transformer for Generalized 3D Pose Transfer [95.56457218144983]
  The intuition of this work is to perceive the geometric inconsistency between the given meshes with the powerful self-attention mechanism. We propose a novel geometry-contrastive Transformer that has an efficient 3D structured perceiving ability to the global geometric inconsistencies. We present a latent isometric regularization module together with a novel semi-synthesized dataset for the cross-dataset 3D pose transfer task.
  arXiv  Detail & Related papers  (2021-12-14T13:14:24Z)
• Learning Skeletal Articulations with Neural Blend Shapes [57.879030623284216]
  We develop a neural technique for articulating 3D characters using enveloping with a pre-defined skeletal structure. Our framework learns to rig and skin characters with the same articulation structure. We propose neural blend shapes which improve the deformation quality in the joint regions.
  arXiv  Detail & Related papers  (2021-05-06T05:58:13Z)
• Dense Non-Rigid Structure from Motion: A Manifold Viewpoint [162.88686222340962]
  Non-Rigid Structure-from-Motion (NRSfM) problem aims to recover 3D geometry of a deforming object from its 2D feature correspondences across multiple frames. We show that our approach significantly improves accuracy, scalability, and robustness against noise.
  arXiv  Detail & Related papers  (2020-06-15T09:15:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.