Point Cloud Learning with Transformer

2021-04-28 · Qi Zhong, Xian-Feng Han

Remarkable performance from Transformer networks in Natural Language Processing promote the development of these models in dealing with computer vision tasks such as image recognition and segmentation. In this paper, we introduce a novel framework, called Multi-level Multi-scale Point Transformer (MLMSPT) that works directly on the irregular point clouds for representation learning. Specifically, a point pyramid transformer is investigated to model features with diverse resolutions or scales we defined, followed by a multi-level transformer module to aggregate contextual information from different levels of each scale and enhance their interactions. While a multi-scale transformer module is designed to capture the dependencies among representations across different scales. Extensive evaluation on public benchmark datasets demonstrate the effectiveness and the competitive performance of our methods on 3D shape classification, segmentation tasks.

📄 PDF Abstract BibTeX arXiv:2104.13636

Code (0)

등록된 구현이 없습니다.

Tasks

3D Shape Classification Representation Learning Segmentation Semantic Segmentation

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 $x$…

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…

NoiseTrans: Point Cloud Denoising with Transformers

2023-04-24 · Guangzhe Hou, Guihe Qin, Minghui Sun, Yanhua Liang 외

Point clouds obtained from capture devices or 3D reconstruction techniques are often noisy and interfere with downstream tasks. The paper aims to recover the underlying surface of noisy point clouds. We design a novel mo…

3D Reconstruction Denoising

Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling

2021-11-29 · CVPR 2022 1 · Xumin Yu, Lulu Tang, Yongming Rao, Tiejun Huang 외

We present Point-BERT, a new paradigm for learning Transformers to generalize the concept of BERT to 3D point cloud. Inspired by BERT, we devise a Masked Point Modeling (MPM) task to pre-train point cloud Transformers. S…

3D Point Cloud Classification 3D Point Cloud Linear Classification Few-Shot 3D Point Cloud Classification Few-Shot Point Cloud Classification+2

Point 4D Transformer Networks for Spatio-Temporal Modeling in Point Cloud Videos

2021-06-19 · CVPR 2021 1 · Hehe Fan, Yi Yang, Mohan Kankanhalli

Point cloud videos exhibit irregularities and lack of order along the spatial dimension where points emerge inconsistently across different frames. To capture the dynamics in point cloud videos, point tracking is usu…

3D Action Recognition Action Recognition Point Tracking Semantic Segmentation

PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers

2021-08-19 · ICCV 2021 10 · Xumin Yu, Yongming Rao, Ziyi Wang, Zuyan Liu 외

Point clouds captured in real-world applications are often incomplete due to the limited sensor resolution, single viewpoint, and occlusion. Therefore, recovering the complete point clouds from partial ones becomes an in…

Decoder Inductive Bias Point Cloud Completion Point Cloud Generation+1

Pix4Point: Image Pretrained Standard Transformers for 3D Point Cloud Understanding

2022-08-25 · Guocheng Qian, Abdullah Hamdi, Xingdi Zhang, Bernard Ghanem

While Transformers have achieved impressive success in natural language processing and computer vision, their performance on 3D point clouds is relatively poor. This is mainly due to the limitation of Transformers: a dem…

3D Point Cloud Classification Inductive Bias Point Cloud Classification Semantic Segmentation