2022/04/08 by Axel Berg, Magnus Oskarsson, Berg, Axel +4 · 1 citation
Computer Science · Engineering · #3D Shape Modeling and Analysis #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Image Processing and 3D Reconstruction #Optical measurement and interference techniques #cs.CV
paper · pdf · doi:10.48550/arxiv.2204.03957
Accepted to the 26th International Conference on Pattern Recognition
arxiv created 2022/04/08 · openalex publication_date 2022/04/08 · arxiv updated 2022/04/11 · openalex created_date 2022/04/14 · openalex updated_date 2026/07/31
While the Transformer architecture has become ubiquitous in the machine learning field, its adaptation to 3D shape recognition is non-trivial. Due to its quadratic computational complexity, the self-attention operator quickly becomes inefficient as the set of input points grows larger. Furthermore, we find that the attention mechanism struggles to find useful connections between individual points on a global scale. In order to alleviate these problems, we propose a two-stage Point Transformer-in-Transformer (Point-TnT) approach which combines local and global attention mechanisms, enabling both individual points and patches of points to attend to each other effectively. Experiments on shape classification show that such an approach provides more useful features for downstream tasks than the baseline Transformer, while also being more computationally efficient. In addition, we also extend our method to feature matching for scene reconstruction, showing that it can be used in conjunction with existing scene reconstruction pipelines.