# CA2T-Net: Category-Agnostic 3D Articulation Transfer from Single Image

arXiv: https://arxiv.org/abs/2301.02232 · HTML: https://mlsanity.com/paper/2301.02232/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 33 references that are in the map.
- First posted on arXiv 5 Jan 2023.

## Builds on (most cited first, 25 of 25)

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [SAPIEN: A SimulAted Part-based Interactive ENvironment](https://mlsanity.com/paper/2003.08515/) (2020)
- [PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding](https://mlsanity.com/paper/1812.02713/) (2018)
- [Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation](https://mlsanity.com/paper/1901.02970/) (2019)
- [ABO: Dataset and Benchmarks for Real-World 3D Object Understanding](https://mlsanity.com/paper/2110.06199/) (2021)
- [Where2Act: From Pixels to Actions for Articulated 3D Objects](https://mlsanity.com/paper/2101.02692/) (2021)
- [Category-Level Articulated Object Pose Estimation](https://mlsanity.com/paper/1912.11913/) (2019)
- [Shape2Motion: Joint Analysis of Motion Parts and Attributes from 3D Shapes](https://mlsanity.com/paper/1903.03911/) (2019)
- [LASR: Learning Articulated Shape Reconstruction from a Monocular Video](https://mlsanity.com/paper/2105.02976/) (2021)
- [Resnet in Resnet: Generalizing Residual Architectures](https://mlsanity.com/paper/1603.08029/) (2016)
- [CAPTRA: CAtegory-level Pose Tracking for Rigid and Articulated Objects from Point Clouds](https://mlsanity.com/paper/2104.03437/) (2021)
- [Articulation-aware Canonical Surface Mapping](https://mlsanity.com/paper/2004.00614/) (2020)
- [ScrewNet: Category-Independent Articulation Model Estimation From Depth Images Using Screw Theory](https://mlsanity.com/paper/2008.10518/) (2020)
- [ROCA: Robust CAD Model Retrieval and Alignment from a Single Image](https://mlsanity.com/paper/2112.01988/) (2021)
- [Deep Part Induction from Articulated Object Pairs](https://mlsanity.com/paper/1809.07417/) (2018)
- [Mask2CAD: 3D Shape Prediction by Learning to Segment and Retrieve](https://mlsanity.com/paper/2007.13034/) (2020)
- [OPD: Single-view 3D Openable Part Detection](https://mlsanity.com/paper/2203.16421/) (2022)
- [Self-supervised Neural Articulated Shape and Appearance Models](https://mlsanity.com/paper/2205.08525/) (2022)
- [Pose from Shape: Deep Pose Estimation for Arbitrary 3D Objects](https://mlsanity.com/paper/1906.05105/) (2019)
- [Towards Real-World Category-level Articulation Pose Estimation](https://mlsanity.com/paper/2105.03260/) (2021)
- [Patch2CAD: Patchwise Embedding Learning for In-the-Wild Shape Retrieval from a Single Image](https://mlsanity.com/paper/2108.09368/) (2021)
- [RPM-Net: Recurrent Prediction of Motion and Parts from Point Cloud](https://mlsanity.com/paper/2006.14865/) (2020)
- [Unsupervised Kinematic Motion Detection for Part-segmented 3D Shape Collections](https://mlsanity.com/paper/2206.08497/) (2022)

## Built on by (most cited first, 3 of 3)

- [OPDMulti: Openable Part Detection for Multiple Objects](https://mlsanity.com/paper/2303.14087/) (2023)
- [MonoMobility: Zero-Shot 3D Mobility Analysis from Monocular Videos](https://mlsanity.com/paper/2505.11868/) (2025)
- [Cepheid: Decoupling Scale from Structure for Cross-Family Motion Completion](https://mlsanity.com/paper/2610.18871/) (2026)

## Abstract (arXiv)

We present a neural network approach to transfer the motion from a single image of an articulated object to a rest-state (i.e., unarticulated) 3D model. Our network learns to predict the object's pose, part segmentation, and corresponding motion parameters to reproduce the articulation shown in the input image. The network is composed of three distinct branches that take a shared joint image-shape embedding and is trained end-to-end. Unlike previous methods, our approach is independent of the topology of the object and can work with objects from arbitrary categories. Our method, trained with only synthetic data, can be used to automatically animate a mesh, infer motion from real images, and transfer articulation to functionally similar but geometrically distinct 3D models at test time.