Point Cloud Segmentation

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

1 leaderboard table shown for this task, 1 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

3 datasets 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.

Most implemented papers archive 2025-07-28

30 shown of 115 papers with code (272 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.

• 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.
• Point Transformer
  16 Dec 2020 24 repositories listed
  For example, on the challenging S3DIS dataset for large-scale semantic scene segmentation, the Point Transformer attains an mIoU of 70.
• 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.
• OctFormer: Octree-based Transformers for 3D Point Clouds
  4 May 2023 4 repositories listed Syntology ran 2 of 9 samples · 7 unverified
  To combat this issue, several works divide point clouds into non-overlapping windows and constrain attentions in each local window.
• Stratified Transformer for 3D Point Cloud Segmentation
  28 Mar 2022 4 repositories listed Syntology ran 5 of 12 samples · 7 unverified
  In this paper, we propose Stratified Transformer that is able to capture long-range contexts and demonstrates strong generalization ability and high performance.
• 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…
• PointSIFT: A SIFT-like Network Module for 3D Point Cloud Semantic Segmentation
  2 Jul 2018 4 repositories listed
  Recently, 3D understanding research sheds light on extracting features from point cloud directly, which requires effective shape pattern description of point clouds.
• 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.
• Learning Geometry-Disentangled Representation for Complementary Understanding of 3D Object Point Cloud
  20 Dec 2020 3 repositories listed
  GDANet introduces Geometry-Disentangle Module to dynamically disentangle point clouds into the contour and flat part of 3D objects, respectively denoted by sharp and gentle variation components.
• SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation
  3 Apr 2020 3 repositories listed Syntology ran 0 of 2 samples · 2 unverified
  Using standard convolutions to process such LiDAR images is problematic, as convolution filters pick up local features that are only active in specific regions in the image.
• Deep Learning for 3D Point Clouds: A Survey
  27 Dec 2019 3 repositories listed
  To stimulate future research, this paper presents a comprehensive review of recent progress in deep learning methods for point clouds.
• Fast 3D Line Segment Detection From Unorganized Point Cloud
  8 Jan 2019 3 repositories listed
  This paper presents a very simple but efficient algorithm for 3D line segment detection from large scale unorganized point cloud.
• Generalized Few-shot 3D Point Cloud Segmentation with Vision-Language Model
  20 Mar 2025 2 repositories listed Syntology ran 0 of 3 samples · 3 unverified · 3 pointer-only (licence)
  In this work, we introduce a GFS-PCS framework that synergizes dense but noisy pseudo-labels from 3D VLMs with precise yet sparse few-shot samples to maximize the strengths of both, named GFS-VL.
• Multimodality Helps Few-Shot 3D Point Cloud Semantic Segmentation
  29 Oct 2024 2 repositories listed Syntology ran 0 of 3 samples · 3 unverified · 3 pointer-only (licence)
  Few-shot 3D point cloud segmentation (FS-PCS) aims at generalizing models to segment novel categories with minimal annotated support samples.
• 3D Annotation-Free Learning by Distilling 2D Open-Vocabulary Segmentation Models for Autonomous Driving
  24 May 2024 2 repositories listed Syntology ran 2 of 5 samples · 3 unverified
  We achieved a record-breaking 47.
• Transformer-Based Visual Segmentation: A Survey
  19 Apr 2023 2 repositories listed
  Recently, transformers, a type of neural network based on self-attention originally designed for natural language processing, have considerably surpassed previous convolutional or recurrent approaches in various vision…
• Point Transformer V2: Grouped Vector Attention and Partition-based Pooling
  11 Oct 2022 2 repositories listed
  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.
• A Dataset for Analysing Complex Document Layouts in the Digital Humanities and Its Evaluation with Krippendorff’s Alpha
  20 Sep 2022 2 repositories listed
  The method is adjustable with regard to evaluation strictness, and it can be used in 2D or 3D as well as for a variety of tasks such as semantic segmentation, instance segmentation, and 3D point cloud segmentation.
• Can We Solve 3D Vision Tasks Starting from A 2D Vision Transformer?
  15 Sep 2022 2 repositories listed
  Vision Transformers (ViTs) have proven to be effective, in solving 2D image understanding tasks by training over large-scale image datasets; and meanwhile as a somehow separate track, in modeling the 3D visual world too…
• CoSMix: Compositional Semantic Mix for Domain Adaptation in 3D LiDAR Segmentation
  20 Jul 2022 2 repositories listed
  We propose a new approach of sample mixing for point cloud UDA, namely Compositional Semantic Mix (CoSMix), the first UDA approach for point cloud segmentation based on sample mixing.
• GIPSO: Geometrically Informed Propagation for Online Adaptation in 3D LiDAR Segmentation
  20 Jul 2022 2 repositories listed
  Our experiments show the effectiveness of our segmentation approach on thousands of real-world point clouds.
• AGCN: Adversarial Graph Convolutional Network for 3D Point Cloud Segmentation
  25 Nov 2021 2 repositories listed
  To overcome these problems, we propose a) a graph convolutional network (GCN) in an adversarial learning scheme where a discriminator network provides a segmentation network with informative information to improve…
• Omni-supervised Point Cloud Segmentation via Gradual Receptive Field Component Reasoning
  21 May 2021 2 repositories listed Syntology ran 2 of 9 samples · 7 unverified
  Our method can significantly improve the backbones in all three datasets.
• PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds
  26 Mar 2021 2 repositories listed Syntology ran 4 of 5 samples · 1 unverified
  The key of PAConv is to construct the convolution kernel by dynamically assembling basic weight matrices stored in Weight Bank, where the coefficients of these weight matrices are self-adaptively learned from point…
• Self-Supervised Learning of Lidar Segmentation for Autonomous Indoor Navigation
  10 Dec 2020 2 repositories listed
  We provide insights into our network predictions and show that our approach can also improve the performances of common localization techniques.
• Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion
  7 Dec 2020 2 repositories listed
  In practice, an initial semantic segmentation (SS) of a single sweep point cloud can be achieved by any appealing network and then flows into the semantic scene completion (SSC) module as the input.
• LatticeNet: Fast Point Cloud Segmentation Using Permutohedral Lattices
  12 Dec 2019 2 repositories listed
  Deep convolutional neural networks (CNNs) have shown outstanding performance in the task of semantically segmenting images.
• OpenMaskDINO3D : Reasoning 3D Segmentation via Large Language Model
  5 Jun 2025 1 repository listed
  Although perception systems have made remarkable advancements in recent years, particularly in 2D reasoning segmentation, these systems still rely on explicit human instruction or pre-defined categories to identify…
• APCoTTA: Continual Test-Time Adaptation for Semantic Segmentation of Airborne LiDAR Point Clouds
  15 May 2025 1 repository listed
  Finally, we construct two benchmarks, ISPRSC and H3DC, to address the lack of CTTA benchmarks for ALS point cloud segmentation.

Syntology lines on 13 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.