Transfer learning has long been a key factor in the advancement of many fields including 2D image analysis. Unfortunately, its applicability in 3D data processing has been relatively limited. While several approaches for point cloud transfer learning have been proposed in recent literature, with contrastive learning gaining particular prominence, most existing methods in this domain have only been studied and evaluated in limited scenarios. Most importantly, there is currently a lack of principled understanding of both when and why point cloud transfer learning methods are applicable. Remarkably, even the applicability of standard supervised pre-training is poorly understood. In this work, we conduct the first in-depth quantitative and qualitative investigation of supervised and contrastive pre-training strategies and their utility in downstream 3D tasks. We demonstrate that layer-wise analysis of learned features provides significant insight into the downstream utility of trained networks. Informed by this analysis, we propose a simple geometric regularization strategy, which improves the transferability of supervised pre-training. Our work thus sheds light onto both the specific challenges of point cloud transfer learning, as well as strategies to overcome them.
Nanjing University of Science and Technology（南京理工大学）
Point clouds obtained from 3D sensors are usually sparse. Existing methods mainly focus on upsampling sparse point clouds in a supervised manner by using dense ground truth point clouds. In this paper, we propose a self-supervised point cloud upsampling network (SSPU-Net) to generate dense point clouds without using ground truth. To achieve this, we exploit the consistency between the input sparse point cloud and generated dense point cloud for the shapes and rendered images. Specifically, we first propose a neighbor expansion unit (NEU) to upsample the sparse point clouds, where the local geo…
Point cloud completion addresses filling in the missing parts of a partial point cloud obtained from depth sensors and generating a complete point cloud. Although there has been steep progress in the supervised methods on the synthetic point cloud completion task, it is hardly applicable in real-world scenarios due to the domain gap between the synthetic and real-world datasets or the requirement of prior information. To overcome these limitations, we propose a novel self-supervised framework ACL-SPC for point cloud completion to train and test on the same data. ACL-SPC takes a single partial …
Wangxuan Institute of Computer Technology, Peking University（北京大学王选计算机研究所）；Lane Department of Computer Science and Electrical Engineering, West Virginia University（西弗吉尼亚大学计算机科学与电气工程系）
Point clouds have attracted increasing attention. Significant progress has been made in methods for point cloud analysis, which often requires costly human annotation as supervision. To address this issue, we propose a novel self-contrastive learning for self-supervised point cloud representation learning, aiming to capture both local geometric patterns and nonlocal semantic primitives based on the nonlocal self-similarity of point clouds. The contributions are two-fold: on the one hand, instead of contrasting among different point clouds as commonly employed in contrastive learning, we exploi…
NEC Labs America（NEC美国实验室）；National Yang Ming Chiao Tung University（阳明交通大学）
Self-supervised learning on point clouds has gained a lot of attention recently, since it addresses the label-efficiency and domain-gap problems on point cloud tasks. In this paper, we propose a novel self-supervised framework to learn informative representations from partial point clouds. We leverage partial point clouds scanned by LiDAR that contain both content and pose attributes, and we show that disentangling such two factors from partial point clouds enhances feature representation learning. To this end, our framework consists of three main parts: 1) a completion network to capture holi…
A-STAR（新加坡科技研究局）；National University of Singapore（新加坡国立大学）
Point cloud analysis has received much attention recently; and segmentation is one of the most important tasks. The success of existing approaches is attributed to deep network design and large amount of labelled training data, where the latter is assumed to be always available. However, obtaining 3d point cloud segmentation labels is often very costly in practice. In this work, we propose a weakly supervised point cloud segmentation approach which requires only a tiny fraction of points to be labelled in the training stage. This is made possible by learning gradient approximation and exploita…
Nanjing University of Science and Technology（南京理工大学）
Point cloud semantic segmentation is a crucial task in 3D scene understanding. Existing methods mainly focus on employing a large number of annotated labels for supervised semantic segmentation. Nonetheless, manually labeling such large point clouds for the supervised segmentation task is time-consuming. In order to reduce the number of annotated labels, we propose a semi-supervised semantic point cloud segmentation network, named SSPC-Net, where we train the semantic segmentation network by inferring the labels of unlabeled points from the few annotated 3D points. In our method, we first part…
Weakly supervised point cloud segmentation, i.e. semantically segmenting a point cloud with only a few labeled points in the whole 3D scene, is highly desirable due to the heavy burden of collecting abundant dense annotations for the model training. However, existing methods remain challenging to accurately segment 3D point clouds since limited annotated data may lead to insufficient guidance for label propagation to unlabeled data. Considering the smoothness-based methods have achieved promising progress, in this paper, we advocate applying the consistency constraint under various perturbatio…
University of Chinese Academy of Sciences（中国科学院大学）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；Alibaba Damo Academy（阿里巴巴达摩院）；South China University of Technology（华南理工大学）
Self-supervised learning has not been fully explored for point cloud analysis. Current frameworks are mainly based on point cloud reconstruction. Given only 3D coordinates, such approaches tend to learn local geometric structures and contours, while failing in understanding high level semantic content. Consequently, they achieve unsatisfactory performance in downstream tasks such as classification, segmentation, etc. To fill this gap, we propose a generic Contour-Perturbed Reconstruction Network (CP-Net), which can effectively guide self-supervised reconstruction to learn semantic content in t…
In this paper, we propose the 3DFeat-Net which learns both 3D feature detector and descriptor for point cloud matching using weak supervision. Unlike many existing works, we do not require manual annotation of matching point clusters. Instead, we leverage on alignment and attention mechanisms to learn feature correspondences from GPS/INS tagged 3D point clouds without explicitly specifying them. We create training and benchmark outdoor Lidar datasets, and experiments show that 3DFeat-Net obtains state-of-the-art performance on these gravity-aligned datasets.
King Abdullah University of Science Technology（阿卜杜拉国王科技大学）
We present a self-supervised task on point clouds, in order to learn meaningful point-wise features that encode local structure around each point. Our self-supervised network, named MortonNet, operates directly on unstructured/unordered point clouds. Using a multi-layer RNN, MortonNet predicts the next point in a point sequence created by a popular and fast Space Filling Curve, the Morton-order curve. The final RNN state (coined Morton feature) is versatile and can be used in generic 3D tasks on point clouds. In fact, we show how Morton features can be used to significantly improve performance…
Recent work on 4D point cloud sequences has attracted a lot of attention. However, obtaining exhaustively labeled 4D datasets is often very expensive and laborious, so it is especially important to investigate how to utilize raw unlabeled data. However, most existing self-supervised point cloud representation learning methods only consider geometry from a static snapshot omitting the fact that sequential observations of dynamic scenes could reveal more comprehensive geometric details. And the video representation learning frameworks mostly model motion as image space flows, let alone being 3D-…
Understanding the flow in 3D space of sparsely sampled points between two consecutive time frames is the core stone of modern geometric-driven systems such as VR/AR, Robotics, and Autonomous driving. The lack of real, non-simulated, labeled data for this task emphasizes the importance of self- or un-supervised deep architectures. This work presents a new self-supervised training method and an architecture for the 3D scene flow estimation under occlusions. Here we show that smart multi-layer fusion between flow prediction and occlusion detection outperforms traditional architectures by a large …
Manual annotation of large-scale point cloud dataset for varying tasks such as 3D object classification, segmentation and detection is often laborious owing to the irregular structure of point clouds. Self-supervised learning, which operates without any human labeling, is a promising approach to address this issue. We observe in the real world that humans are capable of mapping the visual concepts learnt from 2D images to understand the 3D world. Encouraged by this insight, we propose CrossPoint, a simple cross-modal contrastive learning approach to learn transferable 3D point cloud representa…
Institute for Aerospace Studies（航空航天研究所）；University of Toronto（多伦多大学）
Reducing the quantity of annotations required for supervised training is vital when labels are scarce and costly. This reduction is especially important for semantic segmentation tasks involving 3D datasets that are often significantly smaller and more challenging to annotate than their image-based counterparts. Self-supervised pre-training on large unlabelled datasets is one way to reduce the amount of manual annotations needed. Previous work has focused on pre-training with point cloud data exclusively; this approach often requires two or more registered views. In the present work, we combin…
National University of Singapore（新加坡国立大学）；ZheJiang University（浙江大学）；Peking University（北京大学）；Tencent Data Platform（腾讯数据平台）；Pengcheng Laboratory（鹏城实验室）
As a promising scheme of self-supervised learning, masked autoencoding has significantly advanced natural language processing and computer vision. Inspired by this, we propose a neat scheme of masked autoencoders for point cloud self-supervised learning, addressing the challenges posed by point cloud's properties, including leakage of location information and uneven information density. Concretely, we divide the input point cloud into irregular point patches and randomly mask them at a high ratio. Then, a standard Transformer based autoencoder, with an asymmetric design and a shifting mask tok…
Self-supervised learning (SSL) has the potential to benefit many applications, particularly those where manually annotating data is cumbersome. One such situation is the semantic segmentation of point clouds. In this context, existing methods employ contrastive learning strategies and define positive pairs by performing various augmentation of point clusters in a single frame. As such, these methods do not exploit the temporal nature of LiDAR data. In this paper, we introduce an SSL strategy that leverages positive pairs in both the spatial and temporal domain. To this end, we design (i) a poi…
University of Alberta（阿尔伯塔大学）；University of Toronto（多伦多大学）；University of Guleph（圭尔夫大学）
This paper presents a novel self-supervised approach to reconstruct human shape and pose from noisy point cloud data. Relying on large amount of dataset with ground-truth annotations, recent learning-based approaches predict correspondences for every vertice on the point cloud; Chamfer distance is usually used to minimize the distance between a deformed template model and the input point cloud. However, Chamfer distance is quite sensitive to noise and outliers, thus could be unreliable to assign correspondences. To address these issues, we model the probability distribution of the input point …
GS-PT: Exploiting 3D Gaussian Splatting for Comprehensive Point Cloud Understanding via Self-supervised Learning
School of Computer Science, Fudan University（复旦大学计算机科学学院）；School of Mechanical Engineering, Tongji University（同济大学机械工程学院）；Academy for Engineering and Technology, Fudan University（复旦大学工程技术研究院）
University of California, Los Angeles（加州大学洛杉矶分校）；Shanghai Jiao Tong University（上海交通大学）；Beijing Institute for General Artificial Intelligence（北京通用人工智能研究院）；Peking University（北京大学）；Tsinghua University（清华大学）
To date, various 3D scene understanding tasks still lack practical and generalizable pre-trained models, primarily due to the intricate nature of 3D scene understanding tasks and their immense variations introduced by camera views, lighting, occlusions, etc. In this paper, we tackle this challenge by introducing a spatio-temporal representation learning (STRL) framework, capable of learning from unlabeled 3D point clouds in a self-supervised fashion. Inspired by how infants learn from visual data in the wild, we explore the rich spatio-temporal cues derived from the 3D data. Specifically, STRL…
In computer-aided design (CAD) community, the point cloud data is pervasively applied in reverse engineering, where the point cloud analysis plays an important role. While a large number of supervised learning methods have been proposed to handle the unordered point clouds and demonstrated their remarkable success, their performance and applicability are limited to the costly data annotation. In this work, we propose a novel self-supervised pretraining model for point cloud learning without human annotations, which relies solely on upsampling operation to perform feature learning of point clou…
Institute for Infocomm Research, A*STAR（新加坡科技研究局资讯通信研究院）；South China University of Technology（华南理工大学）
Addressing the annotation challenge in 3D Point Cloud segmentation has inspired research into weakly supervised learning. Existing approaches mainly focus on exploiting manifold and pseudo-labeling to make use of large unlabeled data points. A fundamental challenge here lies in the large intra-class variations of local geometric structure, resulting in subclasses within a semantic class. In this work, we leverage this intuition and opt for maintaining an individual classifier for each subclass. Technically, we design a multi-prototype classifier, each prototype serves as the classifier weights…
The University of Sydney（悉尼大学）；University of Technology Sydney（悉尼科技大学）
We present a fast feature-metric point cloud registration framework, which enforces the optimisation of registration by minimising a feature-metric projection error without correspondences. The advantage of the feature-metric projection error is robust to noise, outliers and density difference in contrast to the geometric projection error. Besides, minimising the feature-metric projection error does not need to search the correspondences so that the optimisation speed is fast. The principle behind the proposed method is that the feature difference is smallest if point clouds are aligned very w…
Tsinghua University（清华大学）；Institute for AI Industry Research (AIR), Tsinghua University（清华大学人工智能产业研究院（AIR））；Peking University（北京大学）；Intel Labs（英特尔实验室）
Room layout estimation is a long-existing robotic vision task that benefits both environment sensing and motion planning. However, layout estimation using point clouds (PCs) still suffers from data scarcity due to annotation difficulty. As such, we address the semi-supervised setting of this task based upon the idea of model exponential moving averaging. But adapting this scheme to the state-of-the-art (SOTA) solution for PC-based layout estimation is not straightforward. To this end, we define a quad set matching strategy and several consistency losses based upon metrics tailored for layout q…
Masked autoencoding has achieved great success for self-supervised learning in the image and language domains. However, mask based pretraining has yet to show benefits for point cloud understanding, likely due to standard backbones like PointNet being unable to properly handle the training versus testing distribution mismatch introduced by masking during training. In this paper, we bridge this gap by proposing a discriminative mask pretraining Transformer framework, MaskPoint}, for point clouds. Our key idea is to represent the point cloud as discrete occupancy values (1 if part of the point c…
University of California, Merced（加州大学默塞德分校）；Google Research（谷歌研究院）；Indian Institute of Science（印度科学学院）
Reconstructing 3D models from 2D images is one of the fundamental problems in computer vision. In this work, we propose a deep learning technique for 3D object reconstruction from a single image. Contrary to recent works that either use 3D supervision or multi-view supervision, we use only single view images with no pose information during training as well. This makes our approach more practical requiring only an image collection of an object category and the corresponding silhouettes. We learn both 3D point cloud reconstruction and pose estimation networks in a self-supervised manner, making …
Due to the scarcity of annotated scene flow data, self-supervised scene flow learning in point clouds has attracted increasing attention. In the self-supervised manner, establishing correspondences between two point clouds to approximate scene flow is an effective approach. Previous methods often obtain correspondences by applying point-wise matching that only takes the distance on 3D point coordinates into account, introducing two critical issues: (1) it overlooks other discriminative measures, such as color and surface normal, which often bring fruitful clues for accurate matching; and (2) i…
PointMoment:Mixed-Moment-based Self-Supervised Representation Learning for 3D Point Clouds
School of Information Science and Technology, Northwest University（西北大学信息科学与技术学院）；National and Local Joint Engineering Research Center for Cultural Heritage Digitization（文化遗产数字化国家地方联合工程研究中心）
PointJEM: Self-supervised Point Cloud Understanding for Reducing Feature Redundancy via Joint Entropy Maximization
School of Information Science and Technology, Northwest University（西北大学信息科学与技术学院）；National and Local Joint Engineering Research Center for Cultural Heritage Digitization（文化遗产数字化国家地方联合工程研究中心）
A Cross Branch Fusion-Based Contrastive Learning Framework for Point Cloud Self-supervised Learning
Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）；Tsinghua University（清华大学）；Fraunhofer Institute of Optronics, System Technologies and Image Exploitation IOSB（弗劳恩霍夫光电、系统技术和图像处理研究所）
Beihang University（北京航空航天大学）；School of Computer Science and Engineering（计算机科学与工程学院）
Part mobility analysis is a significant aspect required to achieve a functional understanding of 3D objects. It would be natural to obtain part mobility from the continuous part motion of 3D objects. In this study, we introduce a self-supervised method for segmenting motion parts and predicting their motion attributes from a point cloud sequence representing a dynamic object. To sufficiently utilize spatiotemporal information from the point cloud sequence, we generate trajectories by using correlations among successive frames of the sequence instead of directly processing the point clouds. We …
South China University of Technology（华南理工大学）；Inria（法国国家信息与自动化研究所）
Annotation of large-scale 3D data is notoriously cumbersome and costly. As an alternative, weakly-supervised learning alleviates such a need by reducing the annotation by several order of magnitudes. We propose COARSE3D, a novel architecture-agnostic contrastive learning strategy for 3D segmentation. Since contrastive learning requires rich and diverse examples as keys and anchors, we leverage a prototype memory bank capturing class-wise global dataset information efficiently into a small number of prototypes acting as keys. An entropy-driven sampling technique then allows us to select good pi…
Bridging Domain Gap of Point Cloud Representations via Self-Supervised Geometric Augmentation
School of Computer Science, Nanjing University of Information Science & Technology（南京信息工程大学计算机科学与学院）；Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology (CICAEET), Nanjing University of Information Science & Technology（南京信息工程大学江苏省大气环境与装备技术协同创新中心）；School of Electronic and Information Engineering, South China University of Technology（华南理工大学电子与信息工程学院）；Peng Cheng Laboratory（鹏城实验室）；College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics（南京航空航天大学计算机科学与技术学院）
The City College, The City University of New York（纽约市立大学城市学院）；The Graduate Center, The City University of New York（纽约市立大学研究生中心）
Manually annotating complex scene point cloud datasets is both costly and error-prone. To reduce the reliance on labeled data, a new model called SnapshotNet is proposed as a self-supervised feature learning approach, which directly works on the unlabeled point cloud data of a complex 3D scene. The SnapshotNet pipeline includes three stages. In the snapshot capturing stage, snapshots, which are defined as local collections of points, are sampled from the point cloud scene. A snapshot could be a view of a local 3D scan directly captured from the real scene, or a virtual view of such from a larg…
ContrastMotion: Self-supervised Scene Motion Learning for Large-Scale LiDAR Point Clouds
Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；Rhino（犀牛（公司））；The Chinese University of Hong Kong（香港中文大学）；OPPO Research Institute（OPPO研究院）；Zhejiang Lab（之江实验室）；ShanghaiTech University（上海科技大学）
Stanford University（斯坦福大学）；Facebook AI Research（脸书人工智能研究院）
Fitting geometric primitives to 3D point cloud data bridges a gap between low-level digitized 3D data and high-level structural information on the underlying 3D shapes. As such, it enables many downstream applications in 3D data processing. For a long time, RANSAC-based methods have been the gold standard for such primitive fitting problems, but they require careful per-input parameter tuning and thus do not scale well for large datasets with diverse shapes. In this work, we introduce Supervised Primitive Fitting Network (SPFN), an end-to-end neural network that can robustly detect a varying n…
Tsinghua University（清华大学）；Wayne State University（韦恩州立大学）
The task of point cloud upsampling aims to acquire dense and uniform point sets from sparse and irregular point sets. Although significant progress has been made with deep learning models, state-of-the-art methods require ground-truth dense point sets as the supervision, which makes them limited to be trained under synthetic paired training data and not suitable to be under real-scanned sparse data. However, it is expensive and tedious to obtain large numbers of paired sparse-dense point sets as supervision from real-scanned sparse data. To address this problem, we propose a self-supervised po…
Perception and localization are essential for autonomous delivery vehicles, mostly estimated from 3D LiDAR sensors due to their precise distance measurement capability. This paper presents a strategy to obtain the real-time pseudo point cloud instead of the laser sensor from the image sensor. We propose an approach to use different depth estimators to obtain pseudo point clouds like LiDAR to obtain better performance. Moreover, the training and validating strategy of the depth estimator has adopted stereo imagery data to estimate more accurate depth estimation as well as point cloud results. O…
ShanghaiTech University（上海科技大学）；Chinese University of Hong Kong（香港中文大学）；Shanghai Engineering Research Center of Intelligent Vision and Imaging（上海智能视觉成像工程研究中心）
Real scans always miss partial geometries of objects due to the self-occlusions, external-occlusions, and limited sensor resolutions. Point cloud completion aims to refer the complete shapes for incomplete 3D scans of objects. Current deep learning-based approaches rely on large-scale complete shapes in the training process, which are usually obtained from synthetic datasets. It is not applicable for real-world scans due to the domain gap. In this paper, we propose a self-supervised point cloud completion method (TraPCC) for vehicles in real traffic scenes without any complete data. Based on t…
Point Cloud Mixture-of-Domain-Experts Model for 3D Self-supervised Learning
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院，清华大学）；Institute of Perceptual Intelligence, Pengcheng Laboratory（感知智能研究院，鹏城实验室）；College of Computer Science and Software Engineering, Shenzhen University（深圳大学计算机科学与软件工程学院）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学深圳学院）
