Resilient 3D Object Recognition using GR-Net in Sparse Point Clouds

Recognizing three-dimensional (3 Dimensonal) objects is crucial for several uses for computer vision like service robots, self-driving cars and surveillance drones to navigate effectively in complex environments. However, existing classification techniques struggle with challenges such as varying resolutions, noisy data, and diverse object poses. Previous studies have highlighted the limitations of point cloud-based methods in handling sparsity, rotation, and positional variance. In this study, we concurrently address these difficulties with a unique technique to 3D object categorization. Our method leverages the graph structure of point clouds and employs a to develop a strong latent representation of 3D objects using a neural network. This representation achieves invariance to rotation, positional shift, and scaling while remaining resilient to point sparsity. Our technique outperforms existing approaches, as evidenced by experimental findings on the ModelNet40 dataset, which show a 45.0% and 38.1% gain in classification accuracy when employing sparse point clouds, respectively, over existing models.