ArtiLatent: Realistic Articulated 3D Object Generation via Structured Latents
Abstract
We propose ArtiLatent, a generative framework that synthesizes human-made 3D objects with fine-grained geometry, accurate articulation, and realistic appearance. Our approach jointly models part geometry and articulation dynamics by embedding sparse voxel representations and associated articulation properties—including joint type, axis, origin, range, and part category—into a unified latent space via a variational autoencoder. A latent diffusion model is then trained over this space to enable diverse yet physically plausible sampling. To reconstruct photorealistic 3D shapes, we introduce an articulation-aware Gaussian decoder that accounts for articulation-dependent visibility changes (e.g., revealing the interior of a drawer when opened). By conditioning appearance decoding on articulation state, our method assigns plausible texture features to regions that are typically occluded in static poses, significantly improving visual realism across articulation configurations. Extensive experiments on furniture-like objects from PartNet-Mobility and ACD datasets demonstrate that ArtiLatent outperforms existing approaches in geometric consistency and appearance fidelity. Our framework provides a scalable solution for articulated 3D object synthesis and manipulation.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Other methods generate dynamic content or articulated objects, but typically represent motion, rigid-only articulation, or deformation sequences rather than complete skeletal rigs with skinning weights.
“Other methods generate dynamic content or articulated objects Ren et al. [2023], Wu et al. [2025], Chen et al. [2025], Li et al. [2025], but typically represent motion, rigid-only articulation, or deformation sequences rather than complete skeletal rigs with skinning weights.”
From Rigel3D: Rig-aware Latents for Animation-Ready 3D Asset Generation (2026) · cites this paper as Chen et al. [2025]
Cites
V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation
Milletari, F., Navab, N., & Ahmadi, S.-A. (2016) · 2016 Fourth International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2016.79 · Cited by 11,931 · see citing works
3D Gaussian Splatting for Real-Time Radiance Field Rendering
Kerbl, B., Kopanas, G., Leimkuehler, T., & Drettakis, G. (2023) · ACM Transactions on Graphics · doi:10.1145/3592433 · Cited by 6,025 · see citing works
Nerfies: Deformable Neural Radiance Fields
Park, K., Sinha, U., Barron, J. T., Bouaziz, S., Goldman, D. B., Seitz, S. M., & Martin-Brualla, R. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00581 · Cited by 1,114 · see citing works
SAPIEN: A SimulAted Part-Based Interactive ENvironment
Xiang, F., Qin, Y., Mo, K., Xia, Y., Zhu, H., Liu, F., Liu, M., Jiang, H., Yuan, Y., Wang, H., et al. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01111 · Cited by 406 · see citing works
House-GAN: Relational Generative Adversarial Networks for Graph-Constrained House Layout Generation
Nauata, N., Chang, K.-H., Cheng, C.-Y., Mori, G., & Furukawa, Y. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58452-8_10 · Cited by 341 · see citing works
Structured 3D Latents for Scalable and Versatile 3D Generation
Xiang, J., Lv, Z., Xu, S., Yu, D., Wang, R., Zhang, B., Chen, D., Tong, X., & Yang, J. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.02000 · Cited by 318 · see citing works
Li, J., Xu, K., Chaudhuri, S., Yumer, E., Zhang, H., & Guibas, L. J. (2017) · ACM Transactions on Graphics · doi:10.1145/3072959.3073637 · Cited by 296 · see citing works
Gao, L., Yang, J., Wu, T., Yuan, Y.-J., Fu, H., Lai, Y., & Zhang, H. (2019) · ACM Transactions on Graphics · doi:10.1145/3355089.3356488 · Cited by 243 · see citing works
3DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models
Zhang, B., Tang, J., Nießner, M., & Wonka, P. (2023) · ACM Transactions on Graphics · doi:10.1145/3592442 · Cited by 184 · see citing works
Nauata, N., Hosseini, S., Chang, K.-H., Chu, H., Cheng, C.-Y., & Furukawa, Y. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.01342 · Cited by 180 · see citing works
CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets
Zhang, L., Wang, Z., Zhang, Q., Qiu, Q., Pang, A., Jiang, H., Yang, W., Xu, L., & Jingyi Yu, A. (2024) · ACM Transactions on Graphics · doi:10.1145/3658146 · Cited by 173 · see citing works
SceneFormer: Indoor Scene Generation with Transformers
Wang, X., Yeshwanth, C., & Nießner, M. (2021) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv53792.2021.00021 · Cited by 143 · see citing works
Shabani, M. A., Hosseini, S., & Furukawa, Y. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.00529 · Cited by 124 · see citing works
DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesis
Tang, J., Nie, Y., Markhasin, L., Dai, A., Thies, J., & Nießner, M. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.01938 · Cited by 119 · see citing works
Shape2Motion: Joint Analysis of Motion Parts and Attributes From 3D Shapes
Wang, X., Zhou, B., Shi, Y., Chen, X., Zhao, Q., & Xu, K. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00908 · Cited by 104 · see citing works
Wu, Z., Wang, X., Lin, D., Lischinski, D., Cohen-Or, D., & Huang, H. (2019) · ACM Transactions on Graphics · doi:10.1145/3306346.3322956 · Cited by 85 · see citing works
Jones, R. K., Barton, T., Xu, X., Wang, K., Jiang, E., Guerrero, P., Mitra, N. J., & Ritchie, D. (2020) · ACM Transactions on Graphics · doi:10.1145/3414685.3417812 · Cited by 82 · see citing works
JoinABLe: Learning Bottom-up Assembly of Parametric CAD Joints
Willis, K. D. D., Jayaraman, P. K., Chu, H., Tian, Y., Li, Y., Grandi, D., Sanghi, A., Tran, L., Lambourne, J. G., Solar-Lezama, A., et al. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.01539 · Cited by 79 · see citing works
BrepGen: A B-rep Generative Diffusion Model with Structured Latent Geometry
Xu, X., Lambourne, J. G., Jayaraman, P. K., Wang, Z., Willis, K. D. D., & Furukawa, Y. (2024) · ACM Transactions on Graphics · doi:10.1145/3658129 · Cited by 78 · see citing works
Learning Part Generation and Assembly for Structure-Aware Shape Synthesis
Li, J., Niu, C., & Xu, K. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i07.6798 · Cited by 63 · see citing works
ScrewNet: Category-Independent Articulation Model Estimation From Depth Images Using Screw Theory
Jain, A., Lioutikov, R., Chuck, C., & Niekum, S. (2021) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48506.2021.9561132 · Cited by 63 · see citing works
Global-to-local generative model for 3D shapes
Wang, H., Schor, N., Hu, R., Huang, H., Cohen‐Or, D., & Huang, H. F. (2018) · ACM Transactions on Graphics · doi:10.1145/3272127.3275025 · Cited by 62 · see citing works
Learning Generative Models of 3D Structures
Chaudhuri, S., Ritchie, D., Wu, J., Xu, K., & Zhang, H. (2020) · Computer Graphics Forum · doi:10.1111/cgf.14020 · Cited by 61 · see citing works
LEGO-Net: Learning Regular Rearrangements of Objects in Rooms
Wei, Q. A., Ding, S., Park, J. J., Sajnani, R., Poulenard, A., Sridhar, S., & Guibas, L. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01825 · Cited by 60 · cited 1× · see citing works
“Structured generation has also been extended to scene composition [Tang et al. 2024; Wang et al. 2021; Wei et al. 2023] and architectural layout synthesis [Nauata et al. 2020, 2021; Shabani et al. 2023; Tang et al. 2023], where spatial and relational constraints are explicitly encoded.”
SALAD: Part-Level Latent Diffusion for 3D Shape Generation and Manipulation
Koo, J., Yoo, S., Nguyen, M. H., & Sung, M. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01328 · Cited by 41 · see citing works
PARIS: Part-level Reconstruction and Motion Analysis for Articulated Objects
Liu, J., Amiri, A. M., & Savva, M. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00039 · Cited by 38 · see citing works
Graph Transformer GANs for Graph-Constrained House Generation
Tang, H., Zhang, Z., Shi, H., Li, B., Shao, L., Sebe, N., Timofte, R., & Gool, L. V. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.00216 · Cited by 36 · see citing works
3DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusion
Chen, Z., Tang, J., Dong, Y., Cao, Z., Hong, F., Lan, Y., Wang, T., Xie, H., Wu, T., Saito, S., et al. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.02475 · Cited by 31 · see citing works
Self-citationLearning Generative Models of Shape Handles
Gadelha, M., Gori, G., Ceylan, D., Měch, R., Carr, N., Boubekeur, T., Wang, R., & Maji, S. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00048 · Cited by 31 · see citing works
CAGE: Controllable Articulation GEneration
Liu, J., Tam, H. I. I., Amiri, A. M., & Savva, M. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.01693 · Cited by 24 · see citing works
Category-Level Multi-Part Multi-Joint 3D Shape Assembly
Li, Y., Mo, K., Duan, Y., Wang, H., Zhang, J., Shao, L., Matusik, W., & Guibas, L. J. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.00316 · Cited by 19 · see citing works
Guo, J., Xin, Y., Liu, G., Xu, K., Liu, L., & Hu, R. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.02528 · Cited by 17 · see citing works
Unsupervised 3D Shape Reconstruction by Part Retrieval and Assembly
Xu, X., Guerrero, P., Fisher, M., Chaudhuri, S., & Ritchie, D. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.00827 · Cited by 13 · see citing works
ArtFormer: Controllable Generation of Diverse 3D Articulated Objects
Su, J., Feng, Y., Li, Z., Song, J., He, Y., Ren, B., & Xu, B. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.00183 · Cited by 10 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
MonoArt: Progressive Structural Reasoning for Monocular Articulated 3D Reconstruction
Li, H., Xie, H., Xu, J., Wen, B., Hong, F., & Liu, Z. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37464-6_5 · Cited by 1 · see citing works
Rigel3D: Rig-aware Latents for Animation-Ready 3D Asset Generation
Chatzis, N., Loizou, M., & Kalogerakis, E. (2026) · arXiv · doi:10.48550/arxiv.2605.13129
“Other methods generate dynamic content or articulated objects Ren et al. [2023], Wu et al. [2025], Chen et al. [2025], Li et al. [2025], but typically represent motion, rigid-only articulation, or deformation sequences rather than complete skeletal rigs with skinning weights.”
AniGen: Unified S <sup>3</sup> Fields for Animatable 3D Asset Generation
Huang, Y.-H., Zou, Z.-X., He, Y., Chang, C., Pu, C.-F., Yang, Z., Guo, Y.-C., Cao, Y.-P., & Qi, X. (2026) · ACM Transactions on Graphics · doi:10.1145/3811297
PWM-ArtGen: Part World Model for Articulated Object Generation
Zheng, W., & Wu, A. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37556-8_14
K3AS: QoS-Aware Kinematic 3D Asset Service with Cache-Adaptive Progressive Asset Evolution
Ruan, H., Hu, R., Zhang, Z., Wang, W., & Hu, Z. (2026) · IEEE International Conference on Web Services (ICWS) · doi:10.1109/icws72778.2026.00048
- Authors
- Chen, H., Lan, Y., Chen, Y., & Pan, X.
- Affiliations
- Nanyang Technological University (SG)
- Venue
- Proceedings of the SIGGRAPH Asia 2025 Conference Papers
- Publisher
- ACM
- Published
- 2025-12-14
- Pages
- 1-11
- OpenAlex
- W7110023195
- Cited by
- 4
- References
- 34
- Citations by year
- 2026: 4
- FWCI
- 3.83
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- SIGGRAPH Asia Conference Papers (publishedVersion)
- Topics
- Physical Sciences › Engineering › Computational Mechanics › 3D Shape Modeling and Analysis
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
- Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › Computer Graphics and Visualization Techniques
- Keywords
- latent diffusion models, variational autoencoder, joint embedding
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
