R2-MLP: Round-Roll MLP for Multi-View 3D Object Recognition
This work addresses 3D object recognition for computer vision applications, but it is incremental as it builds on existing MLP architectures with a novel view-based extension.
The paper tackles multi-view 3D object recognition by proposing R2-MLP, an MLP-based architecture that extends spatial-shift MLPs to enable communication between patches from different views, achieving competitive performance on ModelNet10 and ModelNet40 datasets.
Recently, vision architectures based exclusively on multi-layer perceptrons (MLPs) have gained much attention in the computer vision community. MLP-like models achieve competitive performance on a single 2D image classification with less inductive bias without hand-crafted convolution layers. In this work, we explore the effectiveness of MLP-based architecture for the view-based 3D object recognition task. We present an MLP-based architecture termed as Round-Roll MLP (R$^2$-MLP). It extends the spatial-shift MLP backbone by considering the communications between patches from different views. R$^2$-MLP rolls part of the channels along the view dimension and promotes information exchange between neighboring views. We benchmark MLP results on ModelNet10 and ModelNet40 datasets with ablations in various aspects. The experimental results show that, with a conceptually simple structure, our R$^2$-MLP achieves competitive performance compared with existing state-of-the-art methods.