ASFM-Net: Asymmetrical Siamese Feature Matching Network for Point Completion
This work addresses the problem of generating complete 3D shapes from partial point clouds for applications in computer vision and robotics, representing a strong specific gain in the field.
The paper tackles object completion from point clouds by proposing ASFM-Net, an asymmetrical Siamese feature matching network, which achieves state-of-the-art performance on benchmarks like Completion3D, outperforming existing methods by about 12%.
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.