# ArtFormer: Controllable Generation of Diverse 3D Articulated Objects

Source: [ArtFormer: Controllable Generation of Diverse 3D Articulated Objects](<https://www.sota2.com/research/paper/68fa77c91e209131cea75540>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-04T04:59:10.370Z

Authors: Jiayi Su, Youhe Feng, Zheng Li, Jinhua Song, Yangfan He, Botao Ren, Botian Xu

Published: 2024-12-10T07:00:05.000Z

## Abstract

This paper presents a novel framework for modeling and conditional generation of 3D articulated objects. Troubled by flexibility-quality tradeoffs, existing methods are often limited to using predefined structures or retrieving shapes from static datasets. To address these challenges, we parameterize an articulated object as a tree of tokens and employ a transformer to generate both the object's high-level geometry code and its kinematic relations. Subsequently, each sub-part's geometry is further decoded using a signed-distance-function (SDF) shape prior, facilitating the synthesis of high-quality 3D shapes. Our approach enables the generation of diverse objects with high-quality geometry and varying number of parts. Comprehensive experiments on conditional generation from text descriptions demonstrate the effectiveness and flexibility of our method.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Part-Decomposed Single-View Articulated Object Generation on PartNet-Mobility (test)](<https://www.sota2.com/research/sota/part-decomposed-single-view-articulated-object-generation-on-partnet-mobility-test.md>): Part-Decomposed Single-View Articulated Object Generation; PartNet-Mobility (test); RS-gIoU: 1.3165.

- [Single-View Articulated Object Generation on ACD](<https://www.sota2.com/research/sota/single-view-articulated-object-generation-on-acd.md>): Single-View Articulated Object Generation; ACD; RS dgIoU: 134.89.

- [Text-Guided Object Alignment](<https://www.sota2.com/research/sota/text-guided-object-alignment.md>): Text-Guided Object Alignment; Text-Guided Object Alignment; CLIP-R@10: 21.98.

- [3D Articulated Object Generation on PartNet-Mobility](<https://www.sota2.com/research/sota/3d-articulated-object-generation-on-partnet-mobility.md>): 3D Articulated Object Generation; PartNet-Mobility; POR: 2.761.

- [3D Articulated Object Generation on PartNet-Mobility (Geo/Kin/Pref Metrics)](<https://www.sota2.com/research/sota/3d-articulated-object-generation-on-partnet-mobility-geo-kin-pref-metrics.md>): 3D Articulated Object Generation; PartNet-Mobility; Geometric Score: 3.95.

- [Articulated Object Generation (Part Retrieval Shape) on PartNet-Mobility (test)](<https://www.sota2.com/research/sota/articulated-object-generation-part-retrieval-shape-on-partnet-mobility-test.md>): Articulated Object Generation (Part Retrieval Shape); PartNet-Mobility (test); POR: 0.253.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2412.07237>)

[PDF](<https://arxiv.org/pdf/2412.07237.pdf>)

[Implementation](<https://github.com/ShuYuMo2003/ArtFormer>)