Few-Shot 3D Point Cloud Classification

Benchmarks archive 2025-07-28

8 leaderboard tables shown for this task, 8 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

1 dataset whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

29 shown of 29 papers with code (31 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Attention Is All You Need
  12 Jun 2017 595 repositories listed Syntology ran 600 of 946 samples · 346 unverified · 451 pointer-only (licence)
  The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration.
• PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
  2 Dec 2016 110 repositories listed Syntology ran 89 of 164 samples · 75 unverified · 90 pointer-only (licence)
  Point cloud is an important type of geometric data structure.
• PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
  7 Jun 2017 68 repositories listed Syntology ran 36 of 67 samples · 31 unverified · 26 pointer-only (licence)
  By exploiting metric space distances, our network is able to learn local features with increasing contextual scales.
• Dynamic Graph CNN for Learning on Point Clouds
  24 Jan 2018 21 repositories listed Syntology ran 16 of 44 samples · 28 unverified · 31 pointer-only (licence)
  Point clouds provide a flexible geometric representation suitable for countless applications in computer graphics; they also comprise the raw output of most 3D data acquisition devices.
• PointCNN: Convolution On 𝒳-Transformed Points
  23 Jan 2018 16 repositories listed
  The proposed method is a generalization of typical CNNs to feature learning from point clouds, thus we call it PointCNN.
• Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining
  5 Feb 2023 5 repositories listed Syntology ran 2 of 5 samples · 3 unverified
  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.
• Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?
  16 Dec 2022 4 repositories listed
  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.
• Masked Autoencoders for Point Cloud Self-supervised Learning
  13 Mar 2022 4 repositories listed Syntology ran 7 of 9 samples · 2 unverified · 1 pointer-only (licence)
  Then, a standard Transformer based autoencoder, with an asymmetric design and a shifting mask tokens operation, learns high-level latent features from unmasked point patches, aiming to reconstruct the masked point…
• ShapeLLM: Universal 3D Object Understanding for Embodied Interaction
  27 Feb 2024 3 repositories listed Syntology ran 9 of 17 samples · 8 unverified
  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.
• Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Models
  14 Apr 2023 3 repositories listed Syntology ran 9 of 14 samples · 5 unverified · 14 pointer-only (licence)
  To conquer this limitation, we propose a novel Instance-aware Dynamic Prompt Tuning (IDPT) strategy for pre-trained point cloud models.
• Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training
  28 May 2022 3 repositories listed
  By fine-tuning on downstream tasks, Point-M2AE achieves 86.
• Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling
  29 Nov 2021 3 repositories listed Syntology ran 4 of 6 samples · 2 unverified
  Inspired by BERT, we devise a Masked Point Modeling (MPM) task to pre-train point cloud Transformers.
• GPr-Net: Geometric Prototypical Network for Point Cloud Few-Shot Learning
  12 Apr 2023 2 repositories listed
  In the realm of 3D-computer vision applications, point cloud few-shot learning plays a critical role.
• Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoders
  13 Dec 2022 2 repositories listed Syntology ran 4 of 6 samples · 2 unverified
  Pre-training by numerous image data has become de-facto for robust 2D representations.
• Masked Discrimination for Self-Supervised Learning on Point Clouds
  21 Mar 2022 2 repositories listed Syntology ran 1 of 2 samples · 1 unverified
  Masked autoencoding has achieved great success for self-supervised learning in the image and language domains.
• Rethinking Masked Representation Learning for 3D Point Cloud Understanding
  26 Dec 2024 1 repository listed
  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)…
• PCP-MAE: Learning to Predict Centers for Point Masked Autoencoders
  16 Aug 2024 1 repository listed
  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…
• Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud
  25 Apr 2024 1 repository listed
  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.
• Towards Compact 3D Representations via Point Feature Enhancement Masked Autoencoders
  17 Dec 2023 1 repository listed
  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…
• Regress Before Construct: Regress Autoencoder for Point Cloud Self-supervised Learning
  25 Sep 2023 1 repository listed
  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…
• Point-LGMask: Local and Global Contexts Embedding for Point Cloud Pre-training with Multi-Ratio Masking
  8 Jun 2023 1 repository listed
  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…
• CrossMoCo: Multi-modal Momentum Contrastive Learning for Point Cloud
  8 Jun 2023 1 repository listed
  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…
• PointGPT: Auto-regressively Generative Pre-training from Point Clouds
  19 May 2023 1 repository listed Syntology ran 5 of 7 samples · 2 unverified
  Large language models (LLMs) based on the generative pre-training transformer (GPT) have demonstrated remarkable effectiveness across a diverse range of downstream tasks.
• A Closer Look at Few-Shot 3D Point Cloud Classification
  31 Mar 2023 1 repository listed
  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.
• Point2Vec for Self-Supervised Representation Learning on Point Clouds
  29 Mar 2023 1 repository listed Syntology ran 4 of 6 samples · 2 unverified
  Recently, the self-supervised learning framework data2vec has shown inspiring performance for various modalities using a masked student-teacher approach.
• CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understanding
  1 Mar 2022 1 repository listed Syntology ran 1 of 2 samples · 1 unverified · 2 pointer-only (licence)
  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.
• Unsupervised Point Cloud Pre-Training via Occlusion Completion
  2 Oct 2020 1 repository listed
  We find that even when we construct a single pre-training dataset (from ModelNet40), this pre-training method improves accuracy across different datasets and encoders, on a wide range of downstream tasks.
• Self-Supervised Few-Shot Learning on Point Clouds
  29 Sep 2020 1 repository listed Syntology ran 4 of 5 samples · 1 unverified · 5 pointer-only (licence)
  We present a comprehensive empirical evaluation of our method on both downstream classification and segmentation tasks and show that supervised methods pre-trained with our self-supervised learning method significantly…
• PointCNN: Convolution On X-Transformed Points
  1 Dec 2018 1 repository listed
  We present a simple and general framework for feature learning from point cloud.

Syntology lines on 15 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.