WalkFormer: 3D mesh analysis via transformer on random walk

A 3D mesh is a popular representation of 3D shapes. For mesh analysis tasks, one typical method is to map 3D mesh data into 1D sequence data with random walk sampling. However, existing random walk-based approaches cannot make full use of attentive regions, which limits the capability of 3D shape analysis. In addition, existing methods process the random walk as sequence data in the discovery order, which results in computational overhead. In this paper, we propose a novel neural framework named WalkFormer, which applies a transformer to a random walk to fully exploit semantic information in a 3D mesh. First, we propose a novel transformer-based framework to learn semantic information from a random walk of a 3D mesh. Second, to capture the attentive regions of the random walk, our approach extends the multi-head self-attention mechanism to specific 3D mesh analysis tasks. To establish the long-range interactions between vertices in the random walk, our approach adopts a novel relative position encoding module. Thus, the local-global information in the random walk can be obtained and learned in our approach. Third, we discover that for 3D mesh analysis, the sequential operations for the random walk sequence are redundant. Different from previous random walk methods, our approach can be executed in a parallelized manner, which greatly improves computational efficiency. Numerous experiments demonstrate the effectiveness of the proposed method on typical 3D shape analysis tasks.

Automated summary

This paper proposes a neural framework named WalkFormer that applies a transformer to random walks in 3D meshes, enabling the utilization of semantic information. The framework incorporates a novel relative position encoding module and a parallelized execution method, improving computational efficiency. Experimental results demonstrate the effectiveness of the proposed method in typical 3D shape analysis tasks.