paper-with-me

Papers

Robust Point Cloud Processing through Positional Embedding

2023-09-01 · Jianqiao Zheng, Xueqian Li, Sameera Ramasinghe, Simon Lucey

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.

📄 PDF Abstract BibTeX arXiv:2309.00339

Code (1)

osiriszjq/RobustPPE 공식 구현 pytorch

Tasks

Point Cloud Classification

Similar Papers 제목 키워드 기반

Deep Positional and Relational Feature Learning for Rotation-Invariant Point Cloud Analysis

2020-11-18 · ECCV 2020 8 · Ruixuan Yu, Xin Wei, Federico Tombari, Jian Sun

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

2021-01-01 · ICCV 2021 10 · Taewon Min, Chonghyuk Song, Eunseok Kim, Inwook Shim

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 Registration

PointTransformerX: Portable and Efficient 3D Point Cloud Processing without Sparse Algorithms

2026-04-27 · Laurenz Reichardt, Nikolas Ebert, Oliver Wasenmüller arxiv

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 Clouds

NIMBA: Towards Robust and Principled Processing of Point Clouds With SSMs

2024-10-31 · Nursena Köprücü, Destiny Okpekpe, Antonio Orvieto

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 Models

CpT: Convolutional Point Transformer for 3D Point Cloud Processing

2021-11-21 · Chaitanya Kaul, Joshua Mitton, Hang Dai, Roderick Murray-Smith

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