Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

© 2026 Papersgraph. All rights reserved.

computer-vision-10

3D Semantic Segmentation

3260 papers • 126 benchmarks • 313 datasets

3D Semantic Segmentation is a computer vision task that involves dividing a 3D point cloud or 3D mesh into semantically meaningful parts or regions. The goal of 3D semantic segmentation is to identify and label different objects and parts within a 3D scene, which can be used for applications such as robotics, autonomous driving, and augmented reality.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in 3d-semantic-segmentation-10

Trend

Dataset

Best Model

Actions

SemanticKITTI

SemanticKITTI

ScanNet200

ScanNet200

SensatUrban

SensatUrban

Libraries

i

Use these libraries to find 3d-semantic-segmentation-10 models and implementations

Pointcept/Pointcept

12 papers 859

Datasets

nuScenes

SemanticKITTI

S3DIS

KITTI-360

PartNet

SemanticPOSS

Subtasks

Robust 3D Semantic Segmentation Real-Time 3D Semantic Segmentation Unsupervised 3D Semantic Segmentation furniture segmentation furniture segmentation

Most implemented papers

PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation

C. Qi, Hao Su, Kaichun Mo, L. Guibas•Thu Dec 01 2016

This paper designs a novel type of neural network that directly consumes point clouds, which well respects the permutation invariance of points in the input and provides a unified architecture for applications ranging from object classification, part segmentation, to scene semantic parsing.

16162

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

DALES

DALES

S3DIS

S3DIS

PartNet

PartNet

KITTI-360

KITTI-360

ScribbleKITTI

ScribbleKITTI

STPLS3D

STPLS3D

RELLIS-3D Dataset

RELLIS-3D Dataset

nuScenes

nuScenes

3D Platelet EM

3D Platelet EM

ldkong1205/Robo3D

4 papers 255

isl-org/Open3D-ML

3 papers 1,567

facebookresearch/SparseConvNet

2 papers 1,962

yangyanli/PointCNN

2 papers 1,341

vinits5/learning3d

2 papers 606

PaddlePaddle/Paddle3D

2 papers 506

SemanticPOSS

AMOS

STPLS3D

RELLIS-3D

nuScenes-C

3D Point Cloud Part Segmentation

0

PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space

C. Qi, Hao Su, L. Guibas, L. Yi•Tue Jun 06 2017

A hierarchical neural network that applies PointNet recursively on a nested partitioning of the input point set and proposes novel set learning layers to adaptively combine features from multiple scales to learn deep point set features efficiently and robustly.

12754 0

Point Transformer

Nico Engel, Vasileios Belagiannis, K. Dietmayer•Sun Nov 01 2020

This work proposes SortNet, as part of the Point Transformer, which induces input permutation invariance by selecting points based on a learned score, to extract local and global features and relate both representations by introducing the local-global attention mechanism.

2509 0

Dynamic Graph CNN for Learning on Point Clouds

M. Bronstein, Ziwei Liu, Yue Wang, Yongbin Sun, S. Sarma, J. Solomon•Tue Jan 23 2018

This work proposes a new neural network module suitable for CNN-based high-level tasks on point clouds, including classification and segmentation called EdgeConv, which acts on graphs dynamically computed in each layer of the network.

6827 0

KPConv: Flexible and Deformable Convolution for Point Clouds

C. Qi, L. Guibas, Jean-Emmanuel Deschaud, F. Goulette, Hugues Thomas, B. Marcotegui•Wed Apr 17 2019

KPConv is a new design of point convolution, i.e. that operates on point clouds without any intermediate representation, that outperform state-of-the-art classification and segmentation approaches on several datasets.

3040 0

SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloud

K. Keutzer, Bichen Wu, Alvin Wan, Xiangyu Yue•Wed Oct 18 2017

An end-to-end pipeline called SqueezeSeg based on convolutional neural networks (CNN), which takes a transformed LiDAR point cloud as input and directly outputs a point-wise label map, which is then refined by a conditional random field (CRF) implemented as a recurrent layer.

889 0

4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks

S. Savarese, JunYoung Gwak, C. Choy•Wed Apr 17 2019

This work creates an open-source auto-differentiation library for sparse tensors that provides extensive functions for high-dimensional convolutional neural networks and proposes the hybrid kernel, a special case of the generalized sparse convolution, and trilateral-stationary conditional random fields that enforce spatio-temporal consistency in the 7D space-time-chroma space.

2153 0

RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds

Qingyong Hu, Bo Yang, A. Trigoni, A. Markham, Linhai Xie, Stefano Rosa, Yulan Guo, Zhihua Wang•Sun Nov 24 2019

This paper introduces RandLA-Net, an efficient and lightweight neural architecture to directly infer per-point semantics for large-scale point clouds, and introduces a novel local feature aggregation module to progressively increase the receptive field for each 3D point, thereby effectively preserving geometric details.

1831 0

3D Semantic Segmentation with Submanifold Sparse Convolutional Networks

L. Maaten, Benjamin Graham, Martin Engelcke•Mon Nov 27 2017

This work introduces new sparse convolutional operations that are designed to process spatially-sparse data more efficiently, and uses them to develop Spatially-Sparse Convolutional networks, which outperform all prior state-of-the-art models on two tasks involving semantic segmentation of 3D point clouds.

1737 0

PartNet: A Large-Scale Benchmark for Fine-Grained and Hierarchical Part-Level 3D Object Understanding

Hao Su, Kaichun Mo, L. Guibas, L. Yi, Angel X. Chang, Shilin Zhu, Subarna Tripathi•Wed Dec 05 2018

This work presents PartNet, a consistent, large-scale dataset of 3D objects annotated with fine-grained, instance-level, and hierarchical 3D part information, and proposes a baseline method for part instance segmentation that is superior performance over existing methods.

850 0

Adding a benchmark result helps the community track progress.

3D Semantic Segmentation | State-of-the-Art