We present point2vec, a self-supervised method for learning point cloud representations through masked prediction of a teacher network's latent features. Building on data2vec, we investigate a limitation of applying this approach to point clouds: positional information associated with masked patches reveals the overall object shape to the student, weakening the learning task even under heavy masking. point2vec addresses this issue by passing only visible patches to the student encoder and introducing a shallow decoder to predict representations for masked patches. The teacher processes the complete point cloud to provide contextualized training targets. These targets capture global context through the teacher's self-attention, providing supervision beyond the local geometry of individual patches. This design conceals masked-patch positions from the student and reduces its computational cost during pre-training. Our ablations show that the decoder alone provides only part of the improvement; concealing positional information is key. After pre-training on ShapeNet, point2vec outperforms the evaluated self-supervised baselines on shape classification on ModelNet40 and ScanObjectNN and few-shot classification on ModelNet40, while achieving competitive part segmentation results on ShapeNetPart.
Self-supervised point cloud representation learning aims to acquire robust and general feature representations from unlabeled data. Recently, masked point modeling-based methods have shown significant performance improvements for point cloud understanding, yet these methods rely on overlapping grouping strategies (k-nearest neighbor algorithm) resulting in early leakage of structural information of mask groups, and overlook the semantic modeling of object components resulting in parts with the same semantics having obvious feature differences due to position differences. In this work, we rethink grouping strategies and pretext tasks that are more suitable for self-supervised point cloud representation learning and propose a novel hierarchical masked representation learning method, including an optimal transport-based hierarchical grouping strategy, a prototype-based part modeling module, and a hierarchical attention encoder. The proposed method enjoys several merits. First, the proposed grouping strategy partitions the point cloud into non-overlapping groups, eliminating the early leakage of structural information in the masked groups. Second, the proposed prototype-based part modeling module dynamically models different object components, ensuring feature consistency on parts with the same semantics. Extensive experiments on four downstream tasks demonstrate that our method surpasses state-of-the-art 3D representation learning methods. Comprehensive ablation studies and visualizations demonstrate the effectiveness of the proposed modules.
Invariance-based and generative methods have shown a conspicuous performance for 3D self-supervised representation learning (SSRL). However, the former relies on hand-crafted data augmentations that introduce bias not universally applicable to all downstream tasks, and the latter indiscriminately reconstructs masked regions, resulting in irrelevant details being saved in the representation space. To solve the problem above, we introduce 3D-JEPA, a novel non-generative 3D SSRL framework. Specifically, we propose a multi-block sampling strategy that produces a sufficiently informative context block and several representative target blocks. We present the context-aware decoder to enhance the reconstruction of the target blocks. Concretely, the context information is fed to the decoder continuously, facilitating the encoder in learning semantic modeling rather than memorizing the context information related to target blocks. Overall, 3D-JEPA predicts the representation of target blocks from a context block using the encoder and context-aware decoder architecture. Various downstream tasks on different datasets demonstrate 3D-JEPA's effectiveness and efficiency, achieving higher accuracy with fewer pretraining epochs, e.g., 88.65% accuracy on PB_T50_RS with 150 pretraining epochs.
Masked autoencoder has been widely explored in point cloud self-supervised learning, whereby the point cloud is generally divided into visible and masked parts. These methods typically include an encoder accepting visible patches (normalized) and corresponding patch centers (position) as input, with the decoder accepting the output of the encoder and the centers (position) of the masked parts to reconstruct each point in the masked patches. Then, the pre-trained encoders are used for downstream tasks. In this paper, we show a motivating empirical result that when directly feeding the centers of masked patches to the decoder without information from the encoder, it still reconstructs well. In other words, the centers of patches are important and the reconstruction objective does not necessarily rely on representations of the encoder, thus preventing the encoder from learning semantic representations. Based on this key observation, we propose a simple yet effective method, i.e., learning to Predict Centers for Point Masked AutoEncoders (PCP-MAE) which guides the model to learn to predict the significant centers and use the predicted centers to replace the directly provided centers. Specifically, we propose a Predicting Center Module (PCM) that shares parameters with the original encoder with extra cross-attention to predict centers. Our method is of high pre-training efficiency compared to other alternatives and achieves great improvement over Point-MAE, particularly surpassing it by 5.50% on OBJ-BG, 6.03% on OBJ-ONLY, and 5.17% on PB-T50-RS for 3D object classification on the ScanObjectNN dataset. The code is available at https://github.com/aHapBean/PCP-MAE.
Recent advancements in self-supervised learning in the point cloud domain have demonstrated significant potential. However, these methods often suffer from drawbacks, including lengthy pre-training time, the necessity of reconstruction in the input space, or the necessity of additional modalities. In order to address these issues, we introduce Point-JEPA, a joint embedding predictive architecture designed specifically for point cloud data. To this end, we introduce a sequencer that orders point cloud patch embeddings to efficiently compute and utilize their proximity based on the indices during target and context selection. The sequencer also allows shared computations of the patch embeddings' proximity between context and target selection, further improving the efficiency. Experimentally, our method achieves competitive results with state-of-the-art methods while avoiding the reconstruction in the input space or additional modality.
The point cloud is a 3D geometric data that lacks a specific structure and is permutation-invariant. The applications of point clouds have gained significant attention recently in the field of vision tasks. However, most existing works on point clouds utilize supervised learning on large labelled data, which are costly and laborious to collect. To this end, unsupervised learning, for example, self-supervised learning, has shown promising performance in various tasks of 2D computer vision and holds the potential in 3D computer vision applications. In this study, we introduce a novel selfsupervised method called CrossMoCo, which learns the representations of unlabelled point cloud data in a multi-modal setup that also utilizes the 2D rendered images of the point clouds. CrossMoCo outperforms existing methods on multimodal self-supervised learning on point cloud by introducing two new concepts: momentum contrastive learning with more negative samples and multiple-view intra-modal contrastive learning. The first component learns from an online encoder and a momentum encoder with a large number of negative samples, which provides consistent learning signals. The second component enforces consistency between different views of the samples of the same modality, thereby improving multimodal representation. We conduct extensive studies on two popular benchmark datasets (ModelNet40 and ScanObjectNN) for linear classification and few-shot learning tasks. Our results demonstrate that CrossMoCo achieves superior performance over existing methods for both tasks on both datasets, achieving up to 4.36% improvement on linear classification and up to 9.2% on few-shot tasks. Our code is available at https://github.com/snehaputul/CrossMoCo.
Self-supervised learning has achieved great success in both natural language processing and 2D vision, where masked modeling is a quite popular pre-training scheme. However, extending masking to 3D point cloud understanding that combines local and global features poses a new challenge. In our work, we present Point-LGMask, a novel method to embed both local and global contexts with multi-ratio masking, which is quite effective for self-supervised feature learning of point clouds but is unfortunately ignored by existing pre-training works. Specifically, to avoid fitting to a fixed masking ratio, we first propose multi-ratio masking, which prompts the encoder to fully explore representative features thanks to tasks of different difficulties. Next, to encourage the embedding of both local and global features, we formulate a compound loss, which consists of (i) a global representation contrastive loss to encourage the cluster assignments of the masked point clouds to be consistent to that of the completed input, and (ii) a local point cloud prediction loss to encourage accurate prediction of masked points. Equipped with our Point-LGMask, we show that our learned representations transfer well to various downstream tasks, including few-shot classification, shape classification, object part segmentation, as well as real-world scene-based 3D object detection and 3D semantic segmentation. Particularly, our model largely advances existing pre-training methods on the difficult few-shot classification task using the real-captured ScanObjectNN dataset by surpassing over 4% to the second-best method. Also, our Point-LGMask achieves 0.4% AP25 and 0.8% AP50 gains on 3D object detection task over the second-best method. 0.4% mAcc and 0.5% mIoU. Codes have been released at https://github.com/TangYuan96/Point-LGMask
This paper presents ShapeLLM, the first 3D Multimodal Large Language Model (LLM) designed for embodied interaction, exploring a universal 3D object understanding with 3D point clouds and languages. ShapeLLM is built upon an improved 3D encoder by extending ReCon to ReCon++ that benefits from multi-view image distillation for enhanced geometry understanding. By utilizing ReCon++ as the 3D point cloud input encoder for LLMs, ShapeLLM is trained on constructed instruction-following data and tested on our newly human-curated benchmark, 3D MM-Vet. ReCon++ and ShapeLLM achieve state-of-the-art performance in 3D geometry understanding and language-unified 3D interaction tasks, such as embodied visual grounding. Project page: https://qizekun.github.io/shapellm/
Learning 3D representation plays a critical role in masked autoencoder (MAE) based pre-training methods for point cloud, including single-modal and cross-modal based MAE. Specifically, although cross-modal MAE methods learn strong 3D representations via the auxiliary of other modal knowledge, they often suffer from heavy computational burdens and heavily rely on massive cross-modal data pairs that are often unavailable, which hinders their applications in practice. Instead, single-modal methods with solely point clouds as input are preferred in real applications due to their simplicity and efficiency. However, such methods easily suffer from limited 3D representations with global random mask input. To learn compact 3D representations, we propose a simple yet effective Point Feature Enhancement Masked Autoencoders (Point-FEMAE), which mainly consists of a global branch and a local branch to capture latent semantic features. Specifically, to learn more compact features, a share-parameter Transformer encoder is introduced to extract point features from the global and local unmasked patches obtained by global random and local block mask strategies, followed by a specific decoder to reconstruct. Meanwhile, to further enhance features in the local branch, we propose a Local Enhancement Module with local patch convolution to perceive fine-grained local context at larger scales. Our method significantly improves the pre-training efficiency compared to cross-modal alternatives, and extensive downstream experiments underscore the state-of-the-art effectiveness, particularly outperforming our baseline (Point-MAE) by 5.16%, 5.00%, and 5.04% in three variants of ScanObjectNN, respectively. The code is available at https://github.com/zyh16143998882/AAAI24-PointFEMAE.
Large language models (LLMs) based on the generative pre-training transformer (GPT) have demonstrated remarkable effectiveness across a diverse range of downstream tasks. Inspired by the advancements of the GPT, we present PointGPT, a novel approach that extends the concept of GPT to point clouds, addressing the challenges associated with disorder properties, low information density, and task gaps. Specifically, a point cloud auto-regressive generation task is proposed to pre-train transformer models. Our method partitions the input point cloud into multiple point patches and arranges them in an ordered sequence based on their spatial proximity. Then, an extractor-generator based transformer decoder, with a dual masking strategy, learns latent representations conditioned on the preceding point patches, aiming to predict the next one in an auto-regressive manner. Our scalable approach allows for learning high-capacity models that generalize well, achieving state-of-the-art performance on various downstream tasks. In particular, our approach achieves classification accuracies of 94.9% on the ModelNet40 dataset and 93.4% on the ScanObjectNN dataset, outperforming all other transformer models. Furthermore, our method also attains new state-of-the-art accuracies on all four few-shot learning benchmarks.
Masked Autoencoders (MAE) have demonstrated promising performance in self-supervised learning for both 2D and 3D computer vision. Nevertheless, existing MAE-based methods still have certain drawbacks. Firstly, the functional decoupling between the encoder and decoder is incomplete, which limits the encoder's representation learning ability. Secondly, downstream tasks solely utilize the encoder, failing to fully leverage the knowledge acquired through the encoder-decoder architecture in the pre-text task. In this paper, we propose Point Regress AutoEncoder (Point-RAE), a new scheme for regressive autoencoders for point cloud self-supervised learning. The proposed method decouples functions between the decoder and the encoder by introducing a mask regressor, which predicts the masked patch representation from the visible patch representation encoded by the encoder and the decoder reconstructs the target from the predicted masked patch representation. By doing so, we minimize the impact of decoder updates on the representation space of the encoder. Moreover, we introduce an alignment constraint to ensure that the representations for masked patches, predicted from the encoded representations of visible patches, are aligned with the masked patch presentations computed from the encoder. To make full use of the knowledge learned in the pre-training stage, we design a new finetune mode for the proposed Point-RAE. Extensive experiments demonstrate that our approach is efficient during pre-training and generalizes well on various downstream tasks. Specifically, our pre-trained models achieve a high accuracy of \textbf{90.28\%} on the ScanObjectNN hardest split and \textbf{94.1\%} accuracy on ModelNet40, surpassing all the other self-supervised learning methods. Our code and pretrained model are public available at: \url{https://github.com/liuyyy111/Point-RAE}.
Point cloud based 3D deep model has wide applications in many applications such as autonomous driving, house robot, and so on. Inspired by the recent prompt learning in natural language processing, this work proposes a novel Multi-view Vision-Prompt Fusion Network (MvNet) for few-shot 3D point cloud classification. MvNet investigates the possibility of leveraging the off-the-shelf 2D pre-trained models to achieve the few-shot classification, which can alleviate the over-dependence issue of the existing baseline models towards the large-scale annotated 3D point cloud data. Specifically, MvNet first encodes a 3D point cloud into multi-view image features for a number of different views. Then, a novel multi-view prompt fusion module is developed to effectively fuse information from different views to bridge the gap between 3D point cloud data and 2D pre-trained models. A set of 2D image prompts can then be derived to better describe the suitable prior knowledge for a large-scale pre-trained image model for few-shot 3D point cloud classification. Extensive experiments on ModelNet, ScanObjectNN, and ShapeNet datasets demonstrate that MvNet achieves new state-of-the-art performance for 3D few-shot point cloud image classification. The source code of this work will be available soon.
Pre-trained point cloud models have found extensive applications in 3D understanding tasks like object classification and part segmentation. However, the prevailing strategy of full fine-tuning in downstream tasks leads to large per-task storage overhead for model parameters, which limits the efficiency when applying large-scale pre-trained models. Inspired by the recent success of visual prompt tuning (VPT), this paper attempts to explore prompt tuning on pre-trained point cloud models, to pursue an elegant balance between performance and parameter efficiency. We find while instance-agnostic static prompting, e.g. VPT, shows some efficacy in downstream transfer, it is vulnerable to the distribution diversity caused by various types of noises in real-world point cloud data. To conquer this limitation, we propose a novel Instance-aware Dynamic Prompt Tuning (IDPT) strategy for pre-trained point cloud models. The essence of IDPT is to develop a dynamic prompt generation module to perceive semantic prior features of each point cloud instance and generate adaptive prompt tokens to enhance the model's robustness. Notably, extensive experiments demonstrate that IDPT outperforms full fine-tuning in most tasks with a mere 7% of the trainable parameters, providing a promising solution to parameter-efficient learning for pre-trained point cloud models. Code is available at \url{https://github.com/zyh16143998882/ICCV23-IDPT}.
In the realm of 3D-computer vision applications, point cloud few-shot learning plays a critical role. However, it poses an arduous challenge due to the sparsity, irregularity, and unordered nature of the data. Current methods rely on complex local geometric extraction techniques such as convolution, graph, and attention mechanisms, along with extensive data-driven pre-training tasks. These approaches contradict the fundamental goal of few-shot learning, which is to facilitate efficient learning. To address this issue, we propose GPr-Net (Geometric Prototypical Network), a lightweight and computationally efficient geometric prototypical network that captures the intrinsic topology of point clouds and achieves superior performance. Our proposed method, IGI++ (Intrinsic Geometry Interpreter++) employs vector-based hand-crafted intrinsic geometry interpreters and Laplace vectors to extract and evaluate point cloud morphology, resulting in improved representations for FSL (Few-Shot Learning). Additionally, Laplace vectors enable the extraction of valuable features from point clouds with fewer points. To tackle the distribution drift challenge in few-shot metric learning, we leverage hyperbolic space and demonstrate that our approach handles intra and inter-class variance better than existing point cloud few-shot learning methods. Experimental results on the ModelNet40 dataset show that GPr-Net outperforms state-of-the-art methods in few-shot learning on point clouds, achieving utmost computational efficiency that is $170\times$ better than all existing works. The code is publicly available at https://github.com/TejasAnvekar/GPr-Net.
In recent years, research on few-shot learning (FSL) has been fast-growing in the 2D image domain due to the less requirement for labeled training data and greater generalization for novel classes. However, its application in 3D point cloud data is relatively under-explored. Not only need to distinguish unseen classes as in the 2D domain, 3D FSL is more challenging in terms of irregular structures, subtle inter-class differences, and high intra-class variances {when trained on a low number of data.} Moreover, different architectures and learning algorithms make it difficult to study the effectiveness of existing 2D FSL algorithms when migrating to the 3D domain. In this work, for the first time, we perform systematic and extensive investigations of directly applying recent 2D FSL works to 3D point cloud related backbone networks and thus suggest a strong learning baseline for few-shot 3D point cloud classification. Furthermore, we propose a new network, Point-cloud Correlation Interaction (PCIA), with three novel plug-and-play components called Salient-Part Fusion (SPF) module, Self-Channel Interaction Plus (SCI+) module, and Cross-Instance Fusion Plus (CIF+) module to obtain more representative embeddings and improve the feature distinction. These modules can be inserted into most FSL algorithms with minor changes and significantly improve the performance. Experimental results on three benchmark datasets, ModelNet40-FS, ShapeNet70-FS, and ScanObjectNN-FS, demonstrate that our method achieves state-of-the-art performance for the 3D FSL task. Code and datasets are available at https://github.com/cgye96/A_Closer_Look_At_3DFSL.
Mainstream 3D representation learning approaches are built upon contrastive or generative modeling pretext tasks, where great improvements in performance on various downstream tasks have been achieved. However, we find these two paradigms have different characteristics: (i) contrastive models are data-hungry that suffer from a representation over-fitting issue; (ii) generative models have a data filling issue that shows inferior data scaling capacity compared to contrastive models. This motivates us to learn 3D representations by sharing the merits of both paradigms, which is non-trivial due to the pattern difference between the two paradigms. In this paper, we propose Contrast with Reconstruct (ReCon) that unifies these two paradigms. ReCon is trained to learn from both generative modeling teachers and single/cross-modal contrastive teachers through ensemble distillation, where the generative student guides the contrastive student. An encoder-decoder style ReCon-block is proposed that transfers knowledge through cross attention with stop-gradient, which avoids pretraining over-fitting and pattern difference issues. ReCon achieves a new state-of-the-art in 3D representation learning, e.g., 91.26% accuracy on ScanObjectNN. Codes have been released at https://github.com/qizekun/ReCon.
The success of deep learning heavily relies on large-scale data with comprehensive labels, which is more expensive and time-consuming to fetch in 3D compared to 2D images or natural languages. This promotes the potential of utilizing models pretrained with data more than 3D as teachers for cross-modal knowledge transferring. In this paper, we revisit masked modeling in a unified fashion of knowledge distillation, and we show that foundational Transformers pretrained with 2D images or natural languages can help self-supervised 3D representation learning through training Autoencoders as Cross-Modal Teachers (ACT). The pretrained Transformers are transferred as cross-modal 3D teachers using discrete variational autoencoding self-supervision, during which the Transformers are frozen with prompt tuning for better knowledge inheritance. The latent features encoded by the 3D teachers are used as the target of masked point modeling, wherein the dark knowledge is distilled to the 3D Transformer students as foundational geometry understanding. Our ACT pretrained 3D learner achieves state-of-the-art generalization capacity across various downstream benchmarks, e.g., 88.21% overall accuracy on ScanObjectNN. Codes have been released at https://github.com/RunpeiDong/ACT.
Pre-training by numerous image data has become de-facto for robust 2D representations. In contrast, due to the expensive data acquisition and annotation, a paucity of large-scale 3D datasets severely hinders the learning for high-quality 3D features. In this paper, we propose an alternative to obtain superior 3D representations from 2D pre-trained models via Image-to-Point Masked Autoencoders, named as I2P-MAE. By self-supervised pre-training, we leverage the well learned 2D knowledge to guide 3D masked autoencoding, which reconstructs the masked point tokens with an encoder-decoder architecture. Specifically, we first utilize off-the-shelf 2D models to extract the multi-view visual features of the input point cloud, and then conduct two types of image-to-point learning schemes on top. For one, we introduce a 2D-guided masking strategy that maintains semantically important point tokens to be visible for the encoder. Compared to random masking, the network can better concentrate on significant 3D structures and recover the masked tokens from key spatial cues. For another, we enforce these visible tokens to reconstruct the corresponding multi-view 2D features after the decoder. This enables the network to effectively inherit high-level 2D semantics learned from rich image data for discriminative 3D modeling. Aided by our image-to-point pre-training, the frozen I2P-MAE, without any fine-tuning, achieves 93.4% accuracy for linear SVM on ModelNet40, competitive to the fully trained results of existing methods. By further fine-tuning on on ScanObjectNN's hardest split, I2P-MAE attains the state-of-the-art 90.11% accuracy, +3.68% to the second-best, demonstrating superior transferable capacity. Code will be available at https://github.com/ZrrSkywalker/I2P-MAE.
Masked Autoencoders (MAE) have shown great potentials in self-supervised pre-training for language and 2D image transformers. However, it still remains an open question on how to exploit masked autoencoding for learning 3D representations of irregular point clouds. In this paper, we propose Point-M2AE, a strong Multi-scale MAE pre-training framework for hierarchical self-supervised learning of 3D point clouds. Unlike the standard transformer in MAE, we modify the encoder and decoder into pyramid architectures to progressively model spatial geometries and capture both fine-grained and high-level semantics of 3D shapes. For the encoder that downsamples point tokens by stages, we design a multi-scale masking strategy to generate consistent visible regions across scales, and adopt a local spatial self-attention mechanism during fine-tuning to focus on neighboring patterns. By multi-scale token propagation, the lightweight decoder gradually upsamples point tokens with complementary skip connections from the encoder, which further promotes the reconstruction from a global-to-local perspective. Extensive experiments demonstrate the state-of-the-art performance of Point-M2AE for 3D representation learning. With a frozen encoder after pre-training, Point-M2AE achieves 92.9% accuracy for linear SVM on ModelNet40, even surpassing some fully trained methods. By fine-tuning on downstream tasks, Point-M2AE achieves 86.43% accuracy on ScanObjectNN, +3.36% to the second-best, and largely benefits the few-shot classification, part segmentation and 3D object detection with the hierarchical pre-training scheme. Code is available at https://github.com/ZrrSkywalker/Point-M2AE.
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 cloud; 0 if not), and perform simple binary classification between masked object points and sampled noise points as the proxy task. In this way, our approach is robust to the point sampling variance in point clouds, and facilitates learning rich representations. We evaluate our pretrained models across several downstream tasks, including 3D shape classification, segmentation, and real-word object detection, and demonstrate state-of-the-art results while achieving a significant pretraining speedup (e.g., 4.1x on ScanNet) compared to the prior state-of-the-art Transformer baseline. Code is available at https://github.com/haotian-liu/MaskPoint.