Iterative Transformer Network for 3D Point Cloud
This addresses the challenge of real-world 3D data processing for applications in robotics and computer vision, though it is incremental as it builds on existing transformer networks.
The paper tackles the problem of learning from partial and unaligned 3D point cloud data by proposing the Iterative Transformer Network (IT-Net), which canonicalizes object pose through iterative rigid transformations, achieving superior performance on tasks like partial shape classification and object part segmentation.
3D point cloud is an efficient and flexible representation of 3D structures. Recently, neural networks operating on point clouds have shown superior performance on 3D understanding tasks such as shape classification and part segmentation. However, performance on such tasks is evaluated on complete shapes aligned in a canonical frame, while real world 3D data are partial and unaligned. A key challenge in learning from partial, unaligned point cloud data is to learn features that are invariant or equivariant with respect to geometric transformations. To address this challenge, we propose the Iterative Transformer Network (IT-Net), a network module that canonicalizes the pose of a partial object with a series of 3D rigid transformations predicted in an iterative fashion. We demonstrate the efficacy of IT-Net as an anytime pose estimator from partial point clouds without using complete object models. Further, we show that IT-Net achieves superior performance over alternative 3D transformer networks on various tasks, such as partial shape classification and object part segmentation.