Characteristic Views Extraction Modal Based-on Deep Reinforcement Learning for 3D Model Retrieval

Weizhi Nie, Weijie Wang, Anan Liu, Chuang Chen

Abstract

In this paper, we propose an effective framework for view-based 3D model retrieval based on reinforcement learning, which aims to extract the most important views from the view set of 3D models for model representation. Since the choice of the representative views can be treated as a Markov decision process (MDP), we model the view extraction as a progressive process through deep reinforcement learning. First, the visual tool developed by OpenGL is utilized to extract 12 rendered pictures in order from a 3D model. Second, these 12 views are fed into the network as a view-based sequence, and then we utilize characteristic views extraction model to extract the most informative views of the 3D model. Finally, a similarity measure between 3D models is performed to complete the last step pf the model retrieval problem. In the experiment section, the classic ModelNet40 is utilized to evaluate the performance of the proposed method. Extensive experiments and corresponding experimental results have demonstrated the superiority of our approach.
BibTeX
@inproceedings{nie2019characteristic,
  author = {Weizhi Nie and Weijie Wang and Anan Liu and Chuang Chen},
  title = {{Characteristic Views Extraction Modal Based-on Deep Reinforcement Learning for 3D Model Retrieval}},
  booktitle = {ICIP},
  year = {2019},
  url = {https://openreview.net/forum?id=jIC6O8pj8a},
}

Loading related content...

Figure