# Unsupervised Pose-Aware Part Decomposition for 3D Articulated Objects

arXiv: https://arxiv.org/abs/2110.04411 · HTML: https://mlsanity.com/paper/2110.04411/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 49 references that are in the map.
- First posted on arXiv 8 Oct 2021.

## Builds on (most cited first, 30 of 36)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Implicit Neural Representations with Periodic Activation Functions](https://mlsanity.com/paper/2006.09661/) (2020)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018)
- [Spectral Normalization for Generative Adversarial Networks](https://mlsanity.com/paper/1802.05957/) (2018)
- [Generating Diverse High-Fidelity Images with VQ-VAE-2](https://mlsanity.com/paper/1906.00446/) (2019)
- [Instance Normalization: The Missing Ingredient for Fast Stylization](https://mlsanity.com/paper/1607.08022/) (2016)
- [End-to-end Recovery of Human Shape and Pose](https://mlsanity.com/paper/1712.06584/) (2017)
- [Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image](https://mlsanity.com/paper/1607.08128/) (2016)
- [SAPIEN: A SimulAted Part-based Interactive ENvironment](https://mlsanity.com/paper/2003.08515/) (2020)
- [3D human pose estimation in video with temporal convolutions and semi-supervised training](https://mlsanity.com/paper/1811.11742/) (2018)
- [3D Menagerie: Modeling the 3D shape and pose of animals](https://mlsanity.com/paper/1611.07700/) (2016)
- [BSP-Net: Generating Compact Meshes via Binary Space Partitioning](https://mlsanity.com/paper/1911.06971/) (2019)
- [Learning Shape Abstractions by Assembling Volumetric Primitives](https://mlsanity.com/paper/1612.00404/) (2016)
- [CvxNet: Learnable Convex Decomposition](https://mlsanity.com/paper/1909.05736/) (2019)
- [3D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutions](https://mlsanity.com/paper/1905.06292/) (2019)
- [Category-Level Articulated Object Pose Estimation](https://mlsanity.com/paper/1912.11913/) (2019)
- [NASA: Neural Articulated Shape Approximation](https://mlsanity.com/paper/1912.03207/) (2019)
- [Superquadrics Revisited: Learning 3D Shape Parsing beyond Cuboids](https://mlsanity.com/paper/1904.09970/) (2019)
- [Shape2Motion: Joint Analysis of Motion Parts and Attributes from 3D Shapes](https://mlsanity.com/paper/1903.03911/) (2019)
- [Three-D Safari: Learning to Estimate Zebra Pose, Shape, and Texture from Images "In the Wild"](https://mlsanity.com/paper/1908.07201/) (2019)
- [Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networks](https://mlsanity.com/paper/2103.10429/) (2021)
- [Unsupervised 3D Pose Estimation with Geometric Self-Supervision](https://mlsanity.com/paper/1904.04812/) (2019)
- [BAE-NET: Branched Autoencoder for Shape Co-Segmentation](https://mlsanity.com/paper/1903.11228/) (2019)
- [Articulation-aware Canonical Surface Mapping](https://mlsanity.com/paper/2004.00614/) (2020)
- [Neural Deformation Graphs for Globally-consistent Non-rigid Reconstruction](https://mlsanity.com/paper/2012.01451/) (2020)
- [Deep Part Induction from Articulated Object Pairs](https://mlsanity.com/paper/1809.07417/) (2018)
- [Im2Struct: Recovering 3D Shape Structure from a Single RGB Image](https://mlsanity.com/paper/1804.05469/) (2018)

## Built on by (most cited first, 12 of 12)

- [ArtGS: Building Interactable Replicas of Complex Articulated Objects via Gaussian Splatting](https://mlsanity.com/paper/2502.19459/) (2025)
- [Building Rearticulable Models for Arbitrary 3D Objects from 4D Point Clouds](https://mlsanity.com/paper/2306.00979/) (2023)
- [Self-Supervised Category-Level Articulated Object Pose Estimation with Part-Level SE(3) Equivariance](https://mlsanity.com/paper/2302.14268/) (2023)
- [NAP: Neural 3D Articulation Prior](https://mlsanity.com/paper/2305.16315/) (2023)
- [Banana: Banach Fixed-Point Network for Pointcloud Segmentation with Inter-Part Equivariance](https://mlsanity.com/paper/2305.16314/) (2023)
- [3D Compositional Zero-shot Learning with DeCompositional Consensus](https://mlsanity.com/paper/2111.14673/) (2021)
- [VideoArtGS: Building Digital Twins of Articulated Objects from Monocular Video](https://mlsanity.com/paper/2509.17647/) (2025)
- [Semi-Weakly Supervised Object Kinematic Motion Prediction](https://mlsanity.com/paper/2303.17774/) (2023)
- [Unsupervised Kinematic Motion Detection for Part-segmented 3D Shape Collections](https://mlsanity.com/paper/2206.08497/) (2022)
- [MovingParts: Motion-based 3D Part Discovery in Dynamic Radiance Field](https://mlsanity.com/paper/2303.05703/) (2023)
- [GEAR: GEometry-motion Alternating Refinement for Articulated Object Modeling with Gaussian Splatting](https://mlsanity.com/paper/2604.07728/) (2026)
- [Recognition of All Categories of Entities by AI](https://mlsanity.com/paper/2208.06590/) (2022)

## Abstract (arXiv)

Articulated objects exist widely in the real world. However, previous 3D generative methods for unsupervised part decomposition are unsuitable for such objects, because they assume a spatially fixed part location, resulting in inconsistent part parsing. In this paper, we propose PPD (unsupervised Pose-aware Part Decomposition) to address a novel setting that explicitly targets man-made articulated objects with mechanical joints, considering the part poses. We show that category-common prior learning for both part shapes and poses facilitates the unsupervised learning of (1) part decomposition with non-primitive-based implicit representation, and (2) part pose as joint parameters under single-frame shape supervision. We evaluate our method on synthetic and real datasets, and we show that it outperforms previous works in consistent part parsing of the articulated objects based on comparable part pose estimation performance to the supervised baseline.