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.
Australian National University（澳大利亚国立大学）；Data61-CSIRO（澳大利亚联邦科学与工业研究组织Data61部门）
Given the rapid development of 3D scanners, point clouds are becoming popular in AI-driven machines. However, point cloud data is inherently sparse and irregular, causing significant difficulties for machine perception. In this work, we focus on the point cloud upsampling task that intends to generate dense high-fidelity point clouds from sparse input data. Specifically, to activate the transformer's strong capability in representing features, we develop a new variant of a multi-head self-attention structure to enhance both point-wise and channel-wise relations of the feature map. In addition,…
University of Waterloo（滑铁卢大学）；Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；University of Oxford（牛津大学）
Transformers have been at the heart of the Natural Language Processing (NLP) and Computer Vision (CV) revolutions. The significant success in NLP and CV inspired exploring the use of Transformers in point cloud processing. However, how do Transformers cope with the irregularity and unordered nature of point clouds? How suitable are Transformers for different 3D representations (e.g., point- or voxel-based)? How competent are Transformers for various 3D processing tasks? As of now, there is still no systematic survey of the research on these issues. For the first time, we provided a comprehensi…
University of Waterloo（滑铁卢大学）；University of Oxford（牛津大学）
Although accurate and fast point cloud classification is a fundamental task in 3D applications, it is difficult to achieve this purpose due to the irregularity and disorder of point clouds that make it challenging to achieve effective and efficient global discriminative feature learning. Lately, 3D Transformers have been adopted to improve point cloud processing. Nevertheless, massive Transformer layers tend to incur huge computational and memory costs. This paper presents a novel hierarchical framework that incorporates convolution with Transformer for point cloud classification, named 3D Con…
The irregular domain and lack of ordering make it challenging to design deep neural networks for point cloud processing. This paper presents a novel framework named Point Cloud Transformer(PCT) for point cloud learning. PCT is based on Transformer, which achieves huge success in natural language processing and displays great potential in image processing. It is inherently permutation invariant for processing a sequence of points, making it well-suited for point cloud learning. To better capture local context within the point cloud, we enhance input embedding with the support of farthest point …
National University of Defense Technology（国防科技大学）；University of Science and Technology of China（中国科学技术大学）
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 channel encoding transformer is proposed in this paper. Specifically, a channel convolution called Transformer-Conv is designed to encode the channel. It can encode feature channels by capturing the potential relationship between coordinates and features. Compared with simply assigning attention weight to each channel, our method aims to encode the channel adaptively. In addition…
Samsung AI Center Moscow（三星莫斯科人工智能中心）；Skolkovo Institute of Science and Technology (Skoltech)（斯科尔科沃科学技术研究院（Skoltech））；Yandex
We present a new versatile building block for deep point cloud processing architectures that is equally suited for diverse tasks. This building block combines the ideas of spatial transformers and multi-view convolutional networks with the efficiency of standard convolutional layers in two and three-dimensional dense grids. The new block operates via multiple parallel heads, whereas each head differentiably rasterizes feature representations of individual points into a low-dimensional space, and then uses dense convolution to propagate information across points. The results of the processing o…
UC San Diego（加州大学圣地亚哥分校）；The Bishop’s School（毕晓普学校）
In this paper, we present Position-to-Structure Attention Transformers (PS-Former), a Transformer-based algorithm for 3D point cloud recognition. PS-Former deals with the challenge in 3D point cloud representation where points are not positioned in a fixed grid structure and have limited feature description (only 3D coordinates ($x, y, z$) for scattered points). Existing Transformer-based architectures in this domain often require a pre-specified feature engineering step to extract point features. Here, we introduce two new aspects in PS-Former: 1) a learnable condensation layer that performs …
Nanjing University of Science and Technology（南京理工大学）；Illinois Institute of Technology（伊利诺伊理工学院）
Place recognition, an algorithm to recognize the re-visited places, plays the role of back-end optimization trigger in a full SLAM system. Many works equipped with deep learning tools, such as MLP, CNN, and transformer, have achieved great improvements in this research field. Point cloud transformer is one of the excellent frameworks for place recognition applied in robotics, but with large memory consumption and expensive computation, it is adverse to widely deploy the various point cloud transformer networks in mobile or embedded devices. To solve this issue, we propose a binary point cloud …
Deep neural networks are widely used for understanding 3D point clouds. At each point convolution layer, features are computed from local neighborhoods of 3D points and combined for subsequent processing in order to extract semantic information. Existing methods adopt the same individual point neighborhoods throughout the network layers, defined by the same metric on the fixed input point coordinates. This common practice is easy to implement but not necessarily optimal. Ideally, local neighborhoods should be different at different layers, as more latent information is extracted at deeper laye…
Nanjing University of Science and Technology（南京理工大学）；University of Macau（澳门大学）
Place recognition or loop closure detection is one of the core components in a full SLAM system. In this paper, aiming at strengthening the relevancy of local neighboring points and the contextual dependency among global points simultaneously, we investigate the exploitation of transformer-based network for feature extraction, and propose a Hierarchical Transformer for Place Recognition (HiTPR). The HiTPR consists of four major parts: point cell generation, short-range transformer (SRT), long-range transformer (LRT) and global descriptor aggregation. Specifically, the point cloud is initially …
Point cloud completion has become increasingly popular among generation tasks of 3D point clouds, as it is a challenging yet indispensable problem to recover the complete shape of a 3D object from its partial observation. In this paper, we propose a novel SeedFormer to improve the ability of detail preservation and recovery in point cloud completion. Unlike previous methods based on a global feature vector, we introduce a new shape representation, namely Patch Seeds, which not only captures general structures from partial inputs but also preserves regional information of local patterns. Then, …
Point cloud completion task aims to predict the missing part of incomplete point clouds and generate complete point clouds with details. In this paper, we propose a novel point cloud completion network, namely CompleteDT. Specifically, features are learned from point clouds with different resolutions, which is sampled from the incomplete input, and are converted to a series of \textit{spots} based on the geometrical structure. Then, the Dense Relation Augment Module (DRA) based on the transformer is proposed to learn features within \textit{spots} and consider the correlation among these \text…
University of Glasgow（格拉斯哥大学）；MBZUAI（穆罕默德·本·扎耶德人工智能大学）
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 Neural Networks as well as previous 3D point cloud processing transformers. It achieves this feat due to its effectiveness in creating a novel and robust attention-based point set embedding through a convolutional projection layer crafted for processing dynamically local point set neighbourhoods. The resultant point set embedding is robust to the permutations of the input points. Ou…
In many vision and robotics applications, it is common that the captured objects are represented by very few points. Most of the existing completion methods are designed for partial point clouds with many points, and they perform poorly or even fail completely in the case of few points. However, due to the lack of detail information, completing objects from few points faces a huge challenge. Inspired by the successful applications of GAN and Transformers in the image-based vision task, we introduce GAN and Transformer techniques to address the above problem. Firstly, the end-to-end encoder-dec…
Tsinghua University（清华大学）；Kuaishou Technology（快手科技）；Wayne State University（韦恩州立大学）
Point cloud completion aims to predict a complete shape in high accuracy from its partial observation. However, previous methods usually suffered from discrete nature of point cloud and unstructured prediction of points in local regions, which makes it hard to reveal fine local geometric details on the complete shape. To resolve this issue, we propose SnowflakeNet with Snowflake Point Deconvolution (SPD) to generate the complete point clouds. The SnowflakeNet models the generation of complete point clouds as the snowflake-like growth of points in 3D space, where the child points are progressiv…
Korea University（高丽大学）；Meta Reality Labs（Meta现实实验室）
Transformers have shown superior performance on various computer vision tasks with their capabilities to capture long-range dependencies. Despite the success, it is challenging to directly apply Transformers on point clouds due to their quadratic cost in the number of points. In this paper, we present a Self-Positioning point-based Transformer (SPoTr), which is designed to capture both local and global shape contexts with reduced complexity. Specifically, this architecture consists of local self-attention and self-positioning point-based global cross-attention. The self-positioning points, ada…
Transformer with its underlying attention mechanism and the ability to capture long-range dependencies makes it become a natural choice for unordered point cloud data. However, separated local regions from the general sampling architecture corrupt the structural information of the instances, and the inherent relationships between adjacent local regions lack exploration, while local structural information is crucial in a transformer-based 3D point cloud model. Therefore, in this paper, we propose a novel module named Local Context Propagation (LCP) to exploit the message passing between neighbo…
Tsinghua University（清华大学）；Tencent PCG（腾讯平台与内容事业群）；Kuaishou Technology（快手科技）；Wayne State University（韦恩州立大学）
Most existing point cloud completion methods suffer from the discrete nature of point clouds and the unstructured prediction of points in local regions, which makes it difficult to reveal fine local geometric details. To resolve this issue, we propose SnowflakeNet with snowflake point deconvolution (SPD) to generate complete point clouds. SPD models the generation of point clouds as the snowflake-like growth of points, where child points are generated progressively by splitting their parent points after each SPD. Our insight into the detailed geometry is to introduce a skip-transformer in the …
Despite recent success in incorporating learning into point cloud registration, many works focus on learning feature descriptors and continue to rely on nearest-neighbor feature matching and outlier filtering through RANSAC to obtain the final set of correspondences for pose estimation. In this work, we conjecture that attention mechanisms can replace the role of explicit feature matching and RANSAC, and thus propose an end-to-end framework to directly predict the final set of correspondences. We use a network architecture consisting primarily of transformer layers containing self and cross at…
Sun Yat-sen University（中山大学）；Shenzhen Campus of Sun Yat-sen University（中山大学深圳校区）；Queen Mary University of London（伦敦玛丽女王大学）；The University of Melbourne（墨尔本大学）
Effective learning of spatial-temporal information within a point cloud sequence is highly important for many down-stream tasks such as 4D semantic segmentation and 3D action recognition. In this paper, we propose a novel framework named Point Spatial-Temporal Transformer (PST2) to learn spatial-temporal representations from dynamic 3D point cloud sequences. Our PST2 consists of two major modules: a Spatio-Temporal Self-Attention (STSA) module and a Resolution Embedding (RE) module. Our STSA module is introduced to capture the spatial-temporal context information across adjacent frames, while …
Environment perception including detection, classification, tracking, and motion prediction are key enablers for automated driving systems and intelligent transportation applications. Fueled by the advances in sensing technologies and machine learning techniques, LiDAR-based sensing systems have become a promising solution. The current challenges of this solution are how to effectively combine different perception tasks into a single backbone and how to efficiently learn the spatiotemporal features directly from point cloud sequences. In this research, we propose a novel spatiotemporal attenti…
Institute for AI Industry Research (AIR), Tsinghua University（清华大学智能产业研究院）；Intel Labs China（英特尔中国研究院）；Peking University（北京大学）
3D scene understanding from point clouds plays a vital role for various robotic applications. Unfortunately, current state-of-the-art methods use separate neural networks for different tasks like object detection or room layout estimation. Such a scheme has two limitations: 1) Storing and running several networks for different tasks are expensive for typical robotic platforms. 2) The intrinsic structure of separate outputs are ignored and potentially violated. To this end, we propose the first transformer architecture that predicts 3D objects and layouts simultaneously, using point cloud input…
Nanjing University of Aeronautics and Astronautics（南京航空航天大学）
Problems such as equipment defects or limited viewpoints will lead the captured point clouds to be incomplete. Therefore, recovering the complete point clouds from the partial ones plays an vital role in many practical tasks, and one of the keys lies in the prediction of the missing part. In this paper, we propose a novel point cloud completion approach namely ProxyFormer that divides point clouds into existing (input) and missing (to be predicted) parts and each part communicates information through its proxies. Specifically, we fuse information into point proxy via feature and position extra…
Southwest University（西南大学）；College of Computer and Information Science（计算机与信息科学学院）
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 co…
Institute of Data Science, National University of Singapore（新加坡国立大学数据科学研究所）；School of Computing, National University of Singapore（新加坡国立大学计算学院）
Automatically localizing a position based on a few natural language instructions is essential for future robots to communicate and collaborate with humans. To approach this goal, we focus on the text-to-point-cloud cross-modal localization problem. Given a textual query, it aims to identify the described location from city-scale point clouds. The task involves two challenges. 1) In city-scale point clouds, similar ambient instances may exist in several locations. Searching each location in a huge point cloud with only instances as guidance may lead to less discriminative signals and incorrect …
Tsinghua University（清华大学）；Wayne State University（韦恩州立大学）；Kuaishou Technology（快手科技）
Point cloud completion concerns to predict missing part for incomplete 3D shapes. A common strategy is to generate complete shape according to incomplete input. However, unordered nature of point clouds will degrade generation of high-quality 3D shapes, as detailed topology and structure of unordered points are hard to be captured during the generative process using an extracted latent code. We address this problem by formulating completion as point cloud deformation process. Specifically, we design a novel neural network, named PMP-Net++, to mimic behavior of an earth mover. It moves each poi…
GPSFormer: A Global Perception and Local Structure Fitting-based Transformer for Point Cloud Understanding
Cyber Security Research Center (CYSREN), Nanyang Technological University（南洋理工大学网络安全研究中心（CYSREN））；College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院）；Institute of Semiconductors, Chinese Academy of Sciences（中国科学院半导体研究所）
Beijing Institute of Technology（北京理工大学）；National University of Singapore（新加坡国立大学）
Recent Transformer-based methods have achieved advanced performance in point cloud registration by utilizing advantages of the Transformer in order-invariance and modeling dependency to aggregate information. However, they still suffer from indistinct feature extraction, sensitivity to noise, and outliers. The reasons are: (1) the adoption of CNNs fails to model global relations due to their local receptive fields, resulting in extracted features susceptible to noise; (2) the shallow-wide architecture of Transformers and lack of positional encoding lead to indistinct feature extraction due to …
Point Cloud Classification Using Content-based Transformer via Clustering in Feature Space
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Purdue School of Engineering and Technology, Indiana University-Purdue University Indianapolis（印第安纳大学-普渡大学印第安纳波利斯分校普渡工程与技术学院）
The University of Hong Kong（香港大学）；Intel Labs（英特尔实验室）；Max Planck Institute（马克斯·普朗克研究所）
As a pioneering work exploring transformer architecture for 3D point cloud understanding, Point Transformer achieves impressive results on multiple highly competitive benchmarks. In this work, we analyze the limitations of the Point Transformer and propose our powerful and efficient Point Transformer V2 model with novel designs that overcome the limitations of previous work. In particular, we first propose group vector attention, which is more effective than the previous version of vector attention. Inheriting the advantages of both learnable weight encoding and multi-head attention, we presen…
