Attention-based Point Cloud Edge Sampling

2023-02-28 · CVPR 2023 1 · Chengzhi Wu, Junwei Zheng, Julius Pfrommer, Jürgen Beyerer

Point cloud sampling is a less explored research topic for this data representation. The most commonly used sampling methods are still classical random sampling and farthest point sampling. With the development of neural networks, various methods have been proposed to sample point clouds in a task-based learning manner. However, these methods are mostly generative-based, rather than selecting points directly using mathematical statistics. Inspired by the Canny edge detection algorithm for images and with the help of the attention mechanism, this paper proposes a non-generative Attention-based Point cloud Edge Sampling method (APES), which captures salient points in the point cloud outline. Both qualitative and quantitative experimental results show the superior performance of our sampling method on common benchmark tasks.

📄 PDF Abstract BibTeX arXiv:2302.14673

Code (1)

JunweiZheng93/APES 공식 구현 pytorch

Tasks

3D Part Segmentation 3D Point Cloud Classification

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…

Position-Wise Feed-Forward Layer 설명 없음

Residual Connection 설명 없음

Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Adam 설명 없음

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

PU-EdgeFormer: Edge Transformer for Dense Prediction in Point Cloud Upsampling

2023-05-02 · Dohoon Kim, Minwoo Shin, Joonki Paik

Despite the recent development of deep learning-based point cloud upsampling, most MLP-based point cloud upsampling methods have limitations in that it is difficult to train the local and global structure of the point cl…

point cloud upsampling

SAMBLE: Shape-Specific Point Cloud Sampling for an Optimal Trade-Off Between Local Detail and Global Uniformity

2025-04-28 · CVPR 2025 1 · Chengzhi Wu, Yuxin Wan, Hao Fu, Julius Pfrommer 외

Driven by the increasing demand for accurate and efficient representation of 3D data in various domains, point cloud sampling has emerged as a pivotal research topic in 3D computer vision. Recently, learning-to-sample me…

APSNet: Attention Based Point Cloud Sampling

2022-10-11 · Yang Ye, Xiulong Yang, Shihao Ji

Processing large point clouds is a challenging task. Therefore, the data is often downsampled to a smaller size such that it can be stored, transmitted and processed more efficiently without incurring significant perform…

3D Point Cloud Classification Knowledge Distillation Point Cloud Classification Self-Supervised Learning

Learnable Skeleton-Aware 3D Point Cloud Sampling

2023-01-01 · CVPR 2023 1 · Cheng Wen, Baosheng Yu, DaCheng Tao

Point cloud sampling is crucial for efficient large-scale point cloud analysis, where learning-to-sample methods have recently received increasing attention from the community for jointly training with downstream tas…

Object Point Cloud Classification Retrieval

Att2CPC: Attention-Guided Lossy Attribute Compression of Point Clouds

2024-10-23 · Kai Liu, Kang You, Pan Gao, Manoranjan Paul

With the great progress of 3D sensing and acquisition technology, the volume of point cloud data has grown dramatically, which urges the development of efficient point cloud compression methods. In this paper, we focus o…

Attribute