Refinement of Predicted Missing Parts Enhance Point Cloud Completion
This work addresses the inefficiency of redundant predictions in point cloud completion for 3D shape reconstruction, representing an incremental improvement over existing methods.
The paper tackles the problem of point cloud completion by proposing an end-to-end neural network that predicts only the missing geometry and refines the merged result, outperforming state-of-the-art methods on the ShapeNet dataset.
Point cloud completion is the task of predicting complete geometry from partial observations using a point set representation for a 3D shape. Previous approaches propose neural networks to directly estimate the whole point cloud through encoder-decoder models fed by the incomplete point set. By predicting the complete model, the current methods compute redundant information because the output also contains the known incomplete input geometry. This paper proposes an end-to-end neural network architecture that focuses on computing the missing geometry and merging the known input and the predicted point cloud. Our method is composed of two neural networks: the missing part prediction network and the merging-refinement network. The first module focuses on extracting information from the incomplete input to infer the missing geometry. The second module merges both point clouds and improves the distribution of the points. Our experiments on ShapeNet dataset show that our method outperforms the state-of-the-art methods in point cloud completion. The code of our methods and experiments is available in \url{https://github.com/ivansipiran/Refinement-Point-Cloud-Completion}.