论文标题
ShapeFormer：通过稀疏表示的基于变压器的形状完成
ShapeFormer: Transformer-based Shape Completion via Sparse Representation
论文作者
论文摘要
我们提出了ShapeFormer，这是一个基于变压器的网络，它会产生对象完成的分布，以不完整的和可能的点云为条件。然后可以对所得分布进行采样以产生可能的完成，每个分布都显示出合理的形状细节，同时忠于输入。为了促进变压器用于3D，我们引入了一个紧凑的3D表示形式，矢量量化了深层隐式函数，该函数利用空间稀疏性表示3D形状的紧密近似，这是简短的离散变量序列。实验表明，就完成质量和多样性而言，ShapeFormer的表现优于先前的艺术，从模棱两可的部分输入中完成了形状的完成。我们还表明，我们的方法有效地处理各种形状类型，不完整的模式和现实世界扫描。
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.
