Litcius/Paper detail

ASFM-Net: Asymmetrical Siamese Feature Matching Network for Point Completion

Yaqi Xia, Yan Xia, Wei Li, Rui Song, Kailang Cao, Uwe Stilla

202190 citationsDOI

Abstract

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.

Topics & Concepts

Margin (machine learning)Computer sciencePoint cloudBenchmark (surveying)Net (polyhedron)Feature (linguistics)Matching (statistics)Artificial intelligencePoint (geometry)EncoderObject (grammar)Pattern recognition (psychology)AlgorithmComputer visionMachine learningMathematicsStatisticsPhilosophyOperating systemGeographyGeometryLinguisticsGeodesy3D Shape Modeling and Analysis3D Surveying and Cultural HeritageImage Processing and 3D Reconstruction