# Semi-Weakly Supervised Object Kinematic Motion Prediction

arXiv: https://arxiv.org/abs/2303.17774 · HTML: https://mlsanity.com/paper/2303.17774/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 36 references that are in the map.
- First posted on arXiv 31 Mar 2023.

## Builds on (most cited first, 21 of 21)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [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)
- [Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning](https://mlsanity.com/paper/1908.02983/) (2019)
- [Label Propagation for Deep Semi-supervised Learning](https://mlsanity.com/paper/1904.04717/) (2019)
- [Weakly Supervised Deep Detection Networks](https://mlsanity.com/paper/1511.02853/) (2015)
- [Category-Level Articulated Object Pose Estimation](https://mlsanity.com/paper/1912.11913/) (2019)
- [Weakly-Supervised Semantic Segmentation via Sub-category Exploration](https://mlsanity.com/paper/2008.01183/) (2020)
- [On Regularized Losses for Weakly-supervised CNN Segmentation](https://mlsanity.com/paper/1803.09569/) (2018)
- [Shape2Motion: Joint Analysis of Motion Parts and Attributes from 3D Shapes](https://mlsanity.com/paper/1903.03911/) (2019)
- [Multiple Instance Detection Network with Online Instance Classifier Refinement](https://mlsanity.com/paper/1704.00138/) (2017)
- [Box-driven Class-wise Region Masking and Filling Rate Guided Loss for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/1904.11693/) (2019)
- [StructureNet: Hierarchical Graph Networks for 3D Shape Generation](https://mlsanity.com/paper/1908.00575/) (2019)
- [Weakly Supervised Cascaded Convolutional Networks](https://mlsanity.com/paper/1611.08258/) (2016)
- [DSG-Net: Learning Disentangled Structure and Geometry for 3D Shape Generation](https://mlsanity.com/paper/2008.05440/) (2020)
- [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)
- [Unsupervised Pose-Aware Part Decomposition for 3D Articulated Objects](https://mlsanity.com/paper/2110.04411/) (2021)

## Built on by (most cited first, 14 of 14)

- [PARIS: Part-level Reconstruction and Motion Analysis for Articulated Objects](https://mlsanity.com/paper/2308.07391/) (2023)
- [NAP: Neural 3D Articulation Prior](https://mlsanity.com/paper/2305.16315/) (2023)
- [PhysPart: Physically Plausible Part Completion for Interactable Objects](https://mlsanity.com/paper/2408.13724/) (2024)
- [Survey on Modeling of Human-made Articulated Objects](https://mlsanity.com/paper/2403.14937/) (2024)
- [CAPT: Category-level Articulation Estimation from a Single Point Cloud Using Transformer](https://mlsanity.com/paper/2402.17360/) (2024)
- [OP-Align: Object-level and Part-level Alignment for Self-supervised Category-level Articulated Object Pose Estimation](https://mlsanity.com/paper/2408.16547/) (2024)
- [MonoMobility: Zero-Shot 3D Mobility Analysis from Monocular Videos](https://mlsanity.com/paper/2505.11868/) (2025)
- [GAPartManip: A Large-scale Part-centric Dataset for Material-Agnostic Articulated Object Manipulation](https://mlsanity.com/paper/2411.18276/) (2024)
- [Part Segmentation and Motion Estimation for Articulated Objects with Dynamic 3D Gaussians](https://mlsanity.com/paper/2506.22718/) (2025)
- [DYNAMO: Dependency-Aware Deep Learning Framework for Articulated Assembly Motion Prediction](https://mlsanity.com/paper/2509.12430/) (2025)
- [sim2art: Accurate Articulated Object Modeling from a Single Video using Synthetic Training Data Only](https://mlsanity.com/paper/2512.07698/) (2025)
- [PAWS: Perception of Articulation in the Wild at Scale from Egocentric Videos](https://mlsanity.com/paper/2603.25539/) (2026)
- [Part2GS: Part-aware Modeling of Articulated Objects using 3D Gaussian Splatting](https://mlsanity.com/paper/2506.17212/) (2025)
- [Canonical Space Representation for 4D Panoptic Segmentation of Articulated Objects](https://mlsanity.com/paper/2511.05356/) (2025)

## Abstract (arXiv)

Given a 3D object, kinematic motion prediction aims to identify the mobile parts as well as the corresponding motion parameters. Due to the large variations in both topological structure and geometric details of 3D objects, this remains a challenging task and the lack of large scale labeled data also constrain the performance of deep learning based approaches. In this paper, we tackle the task of object kinematic motion prediction problem in a semi-weakly supervised manner. Our key observations are two-fold. First, although 3D dataset with fully annotated motion labels is limited, there are existing datasets and methods for object part semantic segmentation at large scale. Second, semantic part segmentation and mobile part segmentation is not always consistent but it is possible to detect the mobile parts from the underlying 3D structure. Towards this end, we propose a graph neural network to learn the map between hierarchical part-level segmentation and mobile parts parameters, which are further refined based on geometric alignment. This network can be first trained on PartNet-Mobility dataset with fully labeled mobility information and then applied on PartNet dataset with fine-grained and hierarchical part-level segmentation. The network predictions yield a large scale of 3D objects with pseudo labeled mobility information and can further be used for weakly-supervised learning with pre-existing segmentation. Our experiments show there are significant performance boosts with the augmented data for previous method designed for kinematic motion prediction on 3D partial scans.