Semi-Weakly Supervised Object Kinematic Motion Prediction

TL;DR

This paper introduces a semi-weakly supervised approach for 3D object kinematic motion prediction, leveraging existing segmentation datasets and graph neural networks to improve performance despite limited fully labeled data.

Contribution

It proposes a novel graph neural network framework that links hierarchical part segmentation to mobile part parameters, enabling semi-weakly supervised learning for kinematic motion prediction.

Findings

Significant performance improvements with augmented data.

Effective use of pseudo labels for weakly supervised learning.

Successful application on 3D partial scans.

Abstract

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.