We tackle the problem of object completion from point clouds and propose a novel point cloud completion network employing an Asymmetrical Siamese Feature Matching strategy, termed as ASFM-Net. Specifically, the Siamese auto-encoder neural network is adopted to map the partial and complete input point cloud into a shared latent space, which can capture detailed shape prior. Then we design an iterative refinement unit to generate complete shapes with fine-grained details by integrating prior information. Experiments are conducted on the PCN dataset and the Completion3D benchmark, demonstrating the state-of-the-art performance of the proposed ASFM-Net. Our method achieves the 1st place in the leaderboard of Completion3D and outperforms existing methods with a large margin, about 12%. The codes and trained models are released publicly at https://github.com/Yan-Xia/ASFM-Net.
@article{arxiv.2104.09587,
title = {ASFM-Net: Asymmetrical Siamese Feature Matching Network for Point Completion},
author = {Yaqi Xia and Yan Xia and Wei Li and Rui Song and Kailang Cao and Uwe Stilla},
journal= {arXiv preprint arXiv:2104.09587},
year = {2021}
}
Comments
Accepted by ACM MM2021. This work achieves the 1st place in the leaderboard of Completion3D