Lune

CVPR2026Top-tier venue

Particulate: Feed-Forward 3D Object Articulation

Ruining Li, Yuxin Yao, Chuanxia Zheng, Christian Rupprecht, Joan Lasenby, Shangzhe Wu, Andrea Vedaldi

Abstract

We introduce Particulate, a feed-forward model that, given a 3D mesh of an object, infers its articulations, including its 3D parts, their kinematic structure, and the motion constraints. The model is based on a transformer network, the Part Articulation Transformer, which predicts all these parameters for all joints. We train the network end-to-end on a diverse collection of articulated 3D assets from public datasets. During inference, Particulate maps the output of the network back to the input mesh, yielding a fully articulated 3D model in seconds, much faster than prior approaches that require per-object optimization. Particulate also works on AI-generated 3D assets, enabling the generation of articulated 3D objects from a single (real or synthetic) image when combined with an off-the-shelf image-to-3D model. We further introduce a new challenging benchmark for 3D articulation estimation curated from high-quality public 3D assets, and redesign the evaluation protocol to be more consistent with human preferences. Empirically, Particulate significantly outperforms state-of-the-art approaches.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

2 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • SimArt: Decomposing Monolithic Meshes into Sim-ready Articulated Assets via MLLM cites Segment Anything
  • 3DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models cites Denoising Diffusion Probabilistic Models
  • AniGen: Unified S3 Fields for Animatable 3D Asset Generation cites 3DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models
  • AniGen: Unified S3 Fields for Animatable 3D Asset Generation cites Denoising Diffusion Probabilistic Models
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers2

  1. SimArt: Decomposing Monolithic Meshes into Sim-ready Articulated Assets via MLLMChuanrui Zhang, Minghan Qin, Yuang Wang, Baifeng Xie et al.SIGGRAPH 2026
  2. AniGen: Unified S3 Fields for Animatable 3D Asset GenerationYihua Huang, Zi-Xin Zou, Yuting He, Chirui Chang et al.SIGGRAPH 2026

Builds on37

  1. Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 35,902 citations
  2. Segment AnythingAlexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao et al.ICCV 2023 · 13,211 citations
  3. D^2NeRF: Self-Supervised Decoupling of Dynamic and Static Objects from a Monocular VideoTianhao Wu, Fangcheng Zhong, Andrea Tagliasacchi, Forrester Cole et al.NeurIPS 2022 · 184 citations
  4. 3DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion ModelsBiao Zhang, Jiapeng Tang, Matthias Nießner, Peter WonkaSIGGRAPH 2023 · 172 citations
  5. A-SDF: Learning Disentangled Signed Distance Functions for Articulated Shape RepresentationJiteng Mu, Weichao Qiu, Adam Kortylewski, Alan L. Yuille et al.ICCV 2021 · 138 citations

Related papers

  1. ART: Articulated Reconstruction TransformerZizhang Li, Cheng Zhang, Zhengqin Li, Henry Howard-Jenkins et al.CVPR 2026 · 12 citations
  2. ArtLLM: Generating Articulated Assets via 3D LLMPenghao Wang, Siyuan Xie, Hongyu Yan, Xianghui Yang et al.CVPR 2026 · 7 citations
  3. SPARK: Sim-ready Part-level Articulated Reconstruction with VLM KnowledgeYumeng He, Ying Jiang, Jiayin Lu, Yin Yang et al.CVPR 2026 · 6 citations
  4. PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion TransformersYuchen Lin, Chenguo Lin, Panwang Pan, Honglei Yan et al.NeurIPS 2025 · 89 citations
  5. MeshArt: Generating Articulated Meshes with Structure-Guided TransformersDaoyi Gao, Yawar Siddiqui, Lei Li, Angela DaiCVPR 2025
Dusk over the sea between two cliffs drawn in fine vertical lines