We present ShapeFormer, a transformer-based network that produces a distribution of object completions, conditioned on incomplete, and possibly noisy, point clouds. The resultant distribution can then be sampled to generate likely completions, each exhibiting plausible shape details while being faithful to the input. To facilitate the use of transformers for 3D, we introduce a compact 3D representation, vector quantized deep implicit function, that utilizes spatial sparsity to represent a close approximation of a 3D shape by a short sequence of discrete variables. Experiments demonstrate that ShapeFormer outperforms prior art for shape completion from ambiguous partial inputs in terms of both completion quality and diversity. We also show that our approach effectively handles a variety of shape types, incomplete patterns, and real-world scans.

翻译：我们推出一个以变压器为基础的网络“形状Former ”, 其生成的天体完成量分布以不完整且可能很吵闹的点云为条件。 由此产生的分布可以抽样来生成可能的完成量, 每一个都展示了可信的形状细节, 同时忠实于输入量。 为了便于3D使用变压器, 我们引入了一个三维代表器, 矢量分解深度隐含功能, 利用空间宽度代表一个3D形状的近似, 由一小串离散变量组成。 实验显示, ShapeFormer 在完成质量和多样性方面, 从模糊的部分投入来看, 超越了形状完成的前艺术。 我们还表明, 我们的方法有效地处理了各种形状类型、 不完整的模式和真实世界扫描 。