Dual Transformer for Point Cloud Analysis

2021-04-27 · Xian-Feng Han, Yi-Fei Jin, Hui-Xian Cheng, Guo-Qiang Xiao

Following the tremendous success of transformer in natural language processing and image understanding tasks, in this paper, we present a novel point cloud representation learning architecture, named Dual Transformer Network (DTNet), which mainly consists of Dual Point Cloud Transformer (DPCT) module. Specifically, by aggregating the well-designed point-wise and channel-wise multi-head self-attention models simultaneously, DPCT module can capture much richer contextual dependencies semantically from the perspective of position and channel. With the DPCT module as a fundamental component, we construct the DTNet for performing point cloud analysis in an end-to-end manner. Extensive quantitative and qualitative experiments on publicly available benchmarks demonstrate the effectiveness of our proposed transformer framework for the tasks of 3D point cloud classification and segmentation, achieving highly competitive performance in comparison with the state-of-the-art approaches.

📄 PDF Abstract BibTeX arXiv:2104.13044

Code (0)

등록된 구현이 없습니다.

Tasks

3D Point Cloud Classification Point Cloud ClassificationPositionRepresentation Learning

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음

Attention 설명 없음

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

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Adaptive Channel Encoding Transformer for Point Cloud Analysis

2021-12-05 · Guoquan Xu, Hezhi Cao, Yifan Zhang, Yanxin Ma 외

Transformer plays an increasingly important role in various computer vision areas and remarkable achievements have also been made in point cloud analysis. Since they mainly focus on point-wise transformer, an adaptive ch…

Point Cloud Classification

Efficient Point Transformer with Dynamic Token Aggregating for LiDAR Point Cloud Processing

2024-05-23 · Dening Lu, Jun Zhou, Kyle, Gao 외

Recently, LiDAR point cloud processing and analysis have made great progress due to the development of 3D Transformers. However, existing 3D Transformer methods usually are computationally expensive and inefficient due t…

PointABM:Integrating Bidirectional State Space Model with Multi-Head Self-Attention for Point Cloud Analysis

2024-06-10 · Jia-Wei Chen, Yu-jie Xiong, Yong-bin Gao

Mamba, based on state space model (SSM) with its linear complexity and great success in classification provide its superiority in 3D point cloud analysis. Prior to that, Transformer has emerged as one of the most promine…

Mamba

DMF-Net: Image-Guided Point Cloud Completion with Dual-Channel Modality Fusion and Shape-Aware Upsampling Transformer

2024-06-25 · Aihua Mao, Yuxuan Tang, Jiangtao Huang, Ying He

In this paper we study the task of a single-view image-guided point cloud completion. Existing methods have got promising results by fusing the information of image into point cloud explicitly or implicitly. However, giv…

Point Cloud Completion

PMT-MAE: Dual-Branch Self-Supervised Learning with Distillation for Efficient Point Cloud Classification

2024-09-03 · Qiang Zheng, Chao Zhang, Jian Sun

Advances in self-supervised learning are essential for enhancing feature extraction and understanding in point cloud processing. This paper introduces PMT-MAE (Point MLP-Transformer Masked Autoencoder), a novel self-supe…

Point Cloud Classification Self-Supervised Learning Transfer Learning