PCN: Point Completion Network
This addresses shape completion for vision and robotics applications, offering a novel approach that is incremental in its decoder design but does not require prior shape knowledge.
The paper tackles shape completion from partial point clouds by proposing PCN, a learning-based method that directly processes raw point clouds without structural assumptions or annotations, achieving realistic completions on inputs with varying incompleteness and noise, such as cars from LiDAR scans in KITTI.
Shape completion, the problem of estimating the complete geometry of objects from partial observations, lies at the core of many vision and robotics applications. In this work, we propose Point Completion Network (PCN), a novel learning-based approach for shape completion. Unlike existing shape completion methods, PCN directly operates on raw point clouds without any structural assumption (e.g. symmetry) or annotation (e.g. semantic class) about the underlying shape. It features a decoder design that enables the generation of fine-grained completions while maintaining a small number of parameters. Our experiments show that PCN produces dense, complete point clouds with realistic structures in the missing regions on inputs with various levels of incompleteness and noise, including cars from LiDAR scans in the KITTI dataset.