MARNet: Multi-Abstraction Refinement Network for 3D Point Cloud Analysis
This work addresses the problem of limited feature interaction in 3D point cloud analysis for computer vision applications, representing an incremental advancement.
The paper tackles the challenge of representation learning from 3D point clouds by proposing MARNet, which enhances feature interaction across different granularities, resulting in a 2% improvement in classification performance and state-of-the-art results on semantic segmentation.
Representation learning from 3D point clouds is challenging due to their inherent nature of permutation invariance and irregular distribution in space. Existing deep learning methods follow a hierarchical feature extraction paradigm in which high-level abstract features are derived from low-level features. However, they fail to exploit different granularity of information due to the limited interaction between these features. To this end, we propose Multi-Abstraction Refinement Network (MARNet) that ensures an effective exchange of information between multi-level features to gain local and global contextual cues while effectively preserving them till the final layer. We empirically show the effectiveness of MARNet in terms of state-of-the-art results on two challenging tasks: Shape classification and Coarse-to-fine grained semantic segmentation. MARNet significantly improves the classification performance by 2% over the baseline and outperforms the state-of-the-art methods on semantic segmentation task.