FreeArt3D: Training-Free Articulated Object Generation using 3D Diffusion

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Chuhao, Liu, Isabella, Wei, Xinyue, Su, Hao, Liu, Minghua
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909885530112000
author Chen, Chuhao
Liu, Isabella
Wei, Xinyue
Su, Hao
Liu, Minghua
author_facet Chen, Chuhao
Liu, Isabella
Wei, Xinyue
Su, Hao
Liu, Minghua
contents Articulated 3D objects are central to many applications in robotics, AR/VR, and animation. Recent approaches to modeling such objects either rely on optimization-based reconstruction pipelines that require dense-view supervision or on feed-forward generative models that produce coarse geometric approximations and often overlook surface texture. In contrast, open-world 3D generation of static objects has achieved remarkable success, especially with the advent of native 3D diffusion models such as Trellis. However, extending these methods to articulated objects by training native 3D diffusion models poses significant challenges. In this work, we present FreeArt3D, a training-free framework for articulated 3D object generation. Instead of training a new model on limited articulated data, FreeArt3D repurposes a pre-trained static 3D diffusion model (e.g., Trellis) as a powerful shape prior. It extends Score Distillation Sampling (SDS) into the 3D-to-4D domain by treating articulation as an additional generative dimension. Given a few images captured in different articulation states, FreeArt3D jointly optimizes the object's geometry, texture, and articulation parameters without requiring task-specific training or access to large-scale articulated datasets. Our method generates high-fidelity geometry and textures, accurately predicts underlying kinematic structures, and generalizes well across diverse object categories. Despite following a per-instance optimization paradigm, FreeArt3D completes in minutes and significantly outperforms prior state-of-the-art approaches in both quality and versatility. Please check our website for more details: https://czzzzh.github.io/FreeArt3D
format Preprint
id arxiv_https___arxiv_org_abs_2510_25765
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FreeArt3D: Training-Free Articulated Object Generation using 3D Diffusion
Chen, Chuhao
Liu, Isabella
Wei, Xinyue
Su, Hao
Liu, Minghua
Computer Vision and Pattern Recognition
Graphics
Articulated 3D objects are central to many applications in robotics, AR/VR, and animation. Recent approaches to modeling such objects either rely on optimization-based reconstruction pipelines that require dense-view supervision or on feed-forward generative models that produce coarse geometric approximations and often overlook surface texture. In contrast, open-world 3D generation of static objects has achieved remarkable success, especially with the advent of native 3D diffusion models such as Trellis. However, extending these methods to articulated objects by training native 3D diffusion models poses significant challenges. In this work, we present FreeArt3D, a training-free framework for articulated 3D object generation. Instead of training a new model on limited articulated data, FreeArt3D repurposes a pre-trained static 3D diffusion model (e.g., Trellis) as a powerful shape prior. It extends Score Distillation Sampling (SDS) into the 3D-to-4D domain by treating articulation as an additional generative dimension. Given a few images captured in different articulation states, FreeArt3D jointly optimizes the object's geometry, texture, and articulation parameters without requiring task-specific training or access to large-scale articulated datasets. Our method generates high-fidelity geometry and textures, accurately predicts underlying kinematic structures, and generalizes well across diverse object categories. Despite following a per-instance optimization paradigm, FreeArt3D completes in minutes and significantly outperforms prior state-of-the-art approaches in both quality and versatility. Please check our website for more details: https://czzzzh.github.io/FreeArt3D
title FreeArt3D: Training-Free Articulated Object Generation using 3D Diffusion
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2510.25765