3D reconstruction based on hierarchical reinforcement learning with transferability

• Published in: Integrated computer-aided engineering Vol. 30; no. 4; pp. 327 - 339
• Main Authors: Li, Lan, He, Fazhi, Fan, Rubin, Fan, Bo, Yan, Xiaohu
• Format: Journal Article
• Language: English
• Published: London, England SAGE Publications 31.08.2023; Sage Publications Ltd
• Subjects: CAD; CAD/CAM; CAE; CAM; Computer aided design; Computer aided engineering; Computer aided manufacturing; Image reconstruction; Reagents; Training; hierarchical reinforcement learning; CAD/CAE/CAM; 3D reconstruction; augmented state space; transferability
• ISSN: 1069-2509; 1875-8835
• DOI: 10.3233/ICA-230710

3D reconstruction is extremely important in CAD (computer-aided design)/CAE (computer-aided Engineering)/CAM (computer-aided manufacturing). For interpretability, reinforcement learning (RL) is used to reconstruct 3D shapes from images by a series of editing actions. However, typical applications of RL for 3D reconstruction face problems. The search space will increase exponentially with the action space due to the curse of dimensionality, which leads to low performance, especially for complex action spaces in 3D reconstruction. Additionally, most works involve training a specific agent for each shape class without learning related experiences from others. Therefore, we present a hierarchical RL approach with transferability to reconstruct 3D shapes (HRLT3D). First, actions are grouped into macro actions that can be chosen by the top-agent. Second, the task is accordingly decomposed into hierarchically simplified sub-tasks solved by sub-agents. Different from classical hierarchical RL (HRL), we propose a sub-agent based on augmented state space (ASS-Sub-Agent) to replace a set of sub-agents, which can speed up the training process due to shared learning and having fewer parameters. Furthermore, the ASS-Sub-Agent is more easily transferred to data of other classes due to the augmented diverse states and the simplified tasks. The experimental results on typical public dataset show that the proposed HRLT3D performs overwhelmingly better than recent baselines. More impressingly, the experiments also demonstrate the extreme transferability of our approach among data of different classes.