Are All Point Clouds Suitable for Completion? Weakly Supervised Quality Evaluation Network for Point Cloud Completion
This work addresses the issue of noisy point clouds degrading system performance for researchers and practitioners in 3D vision and autonomous driving, offering an incremental improvement by adding a pre-processing step.
The paper tackles the problem of real-world point cloud data quality being worse than CAD training data, which impacts completion accuracy, by proposing a quality evaluation network that scores point clouds to aid in selection before completion. The model, validated on KITTI, effectively distinguishes point cloud quality and assists in tasks like detection and flow estimation.
In the practical application of point cloud completion tasks, real data quality is usually much worse than the CAD datasets used for training. A small amount of noisy data will usually significantly impact the overall system's accuracy. In this paper, we propose a quality evaluation network to score the point clouds and help judge the quality of the point cloud before applying the completion model. We believe our scoring method can help researchers select more appropriate point clouds for subsequent completion and reconstruction and avoid manual parameter adjustment. Moreover, our evaluation model is fast and straightforward and can be directly inserted into any model's training or use process to facilitate the automatic selection and post-processing of point clouds. We propose a complete dataset construction and model evaluation method based on ShapeNet. We verify our network using detection and flow estimation tasks on KITTI, a real-world dataset for autonomous driving. The experimental results show that our model can effectively distinguish the quality of point clouds and help in practical tasks.