# OMAD: Object Model with Articulated Deformations for Pose Estimation and Retrieval

arXiv: https://arxiv.org/abs/2112.07334 · HTML: https://mlsanity.com/paper/2112.07334/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 29 references that are in the map.
- First posted on arXiv 14 Dec 2021.

## Builds on (most cited first, 12 of 12)

- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [SAPIEN: A SimulAted Part-based Interactive ENvironment](https://mlsanity.com/paper/2003.08515/) (2020)
- [Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation](https://mlsanity.com/paper/1901.02970/) (2019)
- [PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose Estimation](https://mlsanity.com/paper/1911.04231/) (2019)
- [Category-Level Articulated Object Pose Estimation](https://mlsanity.com/paper/1912.11913/) (2019)
- [A-SDF: Learning Disentangled Signed Distance Functions for Articulated Shape Representation](https://mlsanity.com/paper/2104.07645/) (2021)
- [ScrewNet: Category-Independent Articulation Model Estimation From Depth Images Using Screw Theory](https://mlsanity.com/paper/2008.10518/) (2020)
- [Deep Part Induction from Articulated Object Pairs](https://mlsanity.com/paper/1809.07417/) (2018)
- [Deep Non-Rigid Structure from Motion](https://mlsanity.com/paper/1908.00052/) (2019)
- [Nothing But Geometric Constraints: A Model-Free Method for Articulated Object Pose Estimation](https://mlsanity.com/paper/2012.00088/) (2020)
- [Unsupervised Learning of Category-Specific Symmetric 3D Keypoints from Point Sets](https://mlsanity.com/paper/2003.07619/) (2020)
- [Learning Universal Shape Dictionary for Realtime Instance Segmentation](https://mlsanity.com/paper/2012.01050/) (2020)

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

- [CARTO: Category and Joint Agnostic Reconstruction of ARTiculated Objects](https://mlsanity.com/paper/2303.15782/) (2023)
- [Building Rearticulable Models for Arbitrary 3D Objects from 4D Point Clouds](https://mlsanity.com/paper/2306.00979/) (2023)
- [GarmentTracking: Category-Level Garment Pose Tracking](https://mlsanity.com/paper/2303.13913/) (2023)
- [SC3K: Self-supervised and Coherent 3D Keypoints Estimation from Rotated, Noisy, and Decimated Point Cloud Data](https://mlsanity.com/paper/2308.05410/) (2023)
- [RoSI: Recovering 3D Shape Interiors from Few Articulation Images](https://mlsanity.com/paper/2304.06342/) (2023)
- [SM3: Self-Supervised Multi-task Modeling with Multi-view 2D Images for Articulated Objects](https://mlsanity.com/paper/2401.09133/) (2024)
- [RPMArt: Towards Robust Perception and Manipulation for Articulated Objects](https://mlsanity.com/paper/2403.16023/) (2024)
- [DICArt: Advancing Category-level Articulated Object Pose Estimation in Discrete State-Spaces](https://mlsanity.com/paper/2602.19565/) (2026)
- [SynHLMA:Synthesizing Hand Language Manipulation for Articulated Object with Discrete Human Object Interaction Representation](https://mlsanity.com/paper/2510.25268/) (2025)
- [Flow6D: Discrete-to-Continuous Flow Matching for Efficient and Accurate Category-Level 6D Pose Estimation](https://mlsanity.com/paper/2606.23293/) (2026)
- [Articulated Object Reconstruction from Rest-State Observation](https://mlsanity.com/paper/2607.27749/) (2026)
- [KineDiff3D: Kinematic-Aware Diffusion for Category-Level Articulated Object Shape Reconstruction and Generation](https://mlsanity.com/paper/2510.17137/) (2025)

## Abstract (arXiv)

Articulated objects are pervasive in daily life. However, due to the intrinsic high-DoF structure, the joint states of the articulated objects are hard to be estimated. To model articulated objects, two kinds of shape deformations namely the geometric and the pose deformation should be considered. In this work, we present a novel category-specific parametric representation called Object Model with Articulated Deformations (OMAD) to explicitly model the articulated objects. In OMAD, a category is associated with a linear shape function with shared shape basis and a non-linear joint function. Both functions can be learned from a large-scale object model dataset and fixed as category-specific priors. Then we propose an OMADNet to predict the shape parameters and the joint states from an object's single observation. With the full representation of the object shape and joint states, we can address several tasks including category-level object pose estimation and the articulated object retrieval. To evaluate these tasks, we create a synthetic dataset based on PartNet-Mobility. Extensive experiments show that our simple OMADNet can serve as a strong baseline for both tasks.