Robust Point Cloud Processing through Positional Embedding
End-to-end trained per-point embeddings are an essential ingredient of any state-of-the-art 3D point cloud processing such as detection or alignment. Methods like PointNet, or the more recent point cloud transformer -- and its variants -- all employ learned per-point embeddings. Despite impressive performance, such approaches are sensitive to out-of-distribution (OOD) noise and outliers. In this paper, we explore the role of an analytical per-point embedding based on the criterion of bandwidth. The concept of bandwidth enables us to draw connections with an alternate per-point embedding -- positional embedding, particularly random Fourier features. We present compelling robust results across downstream tasks such as point cloud classification and registration with several categories of OOD noise.
Code (1)
Tasks
Point Cloud ClassificationSimilar Papers 제목 키워드 기반
Deep Positional and Relational Feature Learning for Rotation-Invariant Point Cloud Analysis
In this paper we propose a rotation-invariant deep network for point clouds analysis. Point-based deep networks are commonly designed to recognize roughly aligned 3D shapes based on point coordinates, but suffer from per…
Distinctiveness Oriented Positional Equilibrium for Point Cloud Registration
Recent state-of-the-art learning-based approaches to point cloud registration have largely been based on graph neural networks (GNN). However, these prominent GNN backbones suffer from the indistinguishable features …
Point Cloud RegistrationPointTransformerX: Portable and Efficient 3D Point Cloud Processing without Sparse Algorithms
3D point cloud perception remains tightly coupled to custom CUDA operators for spatial operations, limiting portability and efficiency on non-NVIDIA, AMD, and embedded hardware. We introduce PointTransformerX (PTX), a fu…
Point CloudsNIMBA: Towards Robust and Principled Processing of Point Clouds With SSMs
Transformers have become dominant in large-scale deep learning tasks across various domains, including text, 2D and 3D vision. However, the quadratic complexity of their attention mechanism limits their efficiency as the…
MambaState Space ModelsCpT: Convolutional Point Transformer for 3D Point Cloud Processing
We present CpT: Convolutional point Transformer - a novel deep learning architecture for dealing with the unstructured nature of 3D point cloud data. CpT is an improvement over existing attention-based Convolutions Neura…
SegmentationSemantic Segmentation