Training-Free Point Cloud Recognition Based on Geometric and Semantic Information Fusion
This work addresses the problem of reducing computational costs for point cloud recognition, but it is incremental as it builds on existing training-free approaches by combining features.
The paper tackles the limitation of existing training-free point cloud recognition methods that use only geometric or semantic features by proposing a novel method that integrates both, achieving state-of-the-art performance on benchmarks like ModelNet and ScanObjectNN.
The trend of employing training-free methods for point cloud recognition is becoming increasingly popular due to its significant reduction in computational resources and time costs. However, existing approaches are limited as they typically extract either geometric or semantic features. To address this limitation, we are the first to propose a novel training-free method that integrates both geometric and semantic features. For the geometric branch, we adopt a non-parametric strategy to extract geometric features. In the semantic branch, we leverage a model aligned with text features to obtain semantic features. Additionally, we introduce the GFE module to complement the geometric information of point clouds and the MFF module to improve performance in few-shot settings. Experimental results demonstrate that our method outperforms existing state-of-the-art training-free approaches on mainstream benchmark datasets, including ModelNet and ScanObiectNN.