Surface reconstruction from raw point clouds has been studied for decades in the computer graphics community, which is highly demanded by modeling and rendering applications nowadays. Classic solutions, such as Poisson surface reconstruction, require point normals as extra input to perform reasonable results. Modern transformer-based methods can work without normals, while the results are less fine-grained due to limited encoding performance in local fusion from discrete points. We introduce a novel normalized matrix attention transformer (Tensorformer) to perform high-quality reconstruction. The proposed matrix attention allows for simultaneous point-wise and channel-wise message passing, while the previous vector attention loses neighbor point information across different channels. It brings more degree of freedom in feature learning and thus facilitates better modeling of local geometries. Our method achieves state-of-the-art on two commonly used datasets, ShapeNetCore and ABC, and attains 4% improvements on IOU on ShapeNet. Code can be accessed https://github.com/THHHomas/Tensorformer6.

翻译：从原始点云进行表面重建在计算机图形学领域已研究数十年，当前建模和渲染应用对此需求极高。经典方案（如泊松表面重建）需将点法线作为额外输入才能产生合理结果。现代基于Transformer的方法虽无需法线即可工作，但由于离散点局部融合的编码性能有限，结果精细度不足。我们提出一种新型归一化矩阵注意力Transformer（Tensorformer）以实现高质量重建。相较于传统向量注意力会丢失不同通道间邻域点信息，所提出的矩阵注意力支持逐点与逐通道同步消息传递，为特征学习带来更高自由度，从而更好地建模局部几何结构。本方法在ShapeNetCore和ABC两个常用数据集上达到最优性能，并在ShapeNet上实现交并比（IOU）提升4%。代码访问地址：https://github.com/THHHomas/Tensorformer6