computer-vision-1

LIDAR Semantic Segmentation

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in lidar-semantic-segmentation-1

Trend

Dataset

Best Model

Actions

nuScenes

Paris-Lille-3D

SemanticKITTI

Libraries

i

Use these libraries to find lidar-semantic-segmentation-1 models and implementations

Pointcept/Pointcept

5 papers 1,111

Datasets

Subtasks

No subtasks available.

Most implemented papers

SSD: Single Shot MultiBox Detector

Christian Szegedy, D. Erhan, A. Berg, Scott E. Reed, W. Liu, Dragomir Anguelov, Cheng-Yang Fu•Mon Dec 07 2015

The approach, named SSD, discretizes the output space of bounding boxes into a set of default boxes over different aspect ratios and scales per feature map location, which makes SSD easy to train and straightforward to integrate into systems that require a detection component.

33666

Content

SemanticKITTI

ULS labeled data

ldkong1205/Robo3D

3 papers 271

nuScenes (Cross-City UDA)

ULS labeled data

0

Paper Graph

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

Paper Graph

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

Paper Graph

Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution

Haotian Tang, Yujun Lin, Zhijian Liu, Shengyu Zhao, Ji Lin, Hanrui Wang, Song Han•Thu Jul 30 2020

This work proposes Sparse Point-Voxel Convolution (SPVConv), a lightweight 3D module that equips the vanilla Sparse Convolution with the high-resolution point-based branch, and presents 3D Neural Architecture Search (3D-NAS) to search the optimal network architecture over this diverse design space efficiently and effectively.

777 0

Paper Graph

PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation

H. Foroosh, Xiangyu Yue, Yang Zhang, Zixiang Zhou, P. David, Zerong Xi•Mon Mar 30 2020

This work proposes a new LiDAR-specific, KNN-free segmentation algorithm - PolarNet, which greatly increases the mIoU in three drastically different real urban LiDar single-scan segmentation datasets while retaining ultra low latency and near real-time throughput.

550 0

Paper Graph

LENet: Lightweight And Efficient LiDAR Semantic Segmentation Using Multi-Scale Convolution Attention

Ben Ding•Sat Dec 31 2022

This paper proposes LENet, a lightweight andcient projection-based LiDAR semantic segmentation network, which has an encoder-decoder architecture, and introduces multiple auxiliary segmentation heads to further improve the network accuracy.

15 0

Paper Graph

Cylinder3D: An Effective 3D Framework for Driving-scene LiDAR Semantic Segmentation

Dahua Lin, Hongsheng Li, Xiao Song, Yuexin Ma, Xinge Zhu, Hui Zhou, Zhe Wang•Mon Aug 03 2020

This work develops a 3D cylinder partition and a3D cylinder convolution based framework, termed as Cylinder3D, which exploits the 3D topology relations and structures of driving-scene point clouds and introduces a dimension-decomposition based context modeling module to explore the high-rank context information in point clouds in a progressive manner.

227 0

Paper Graph

Scribble-Supervised LiDAR Semantic Segmentation

L. Gool, Dengxin Dai, Ozan Unal•Tue Mar 15 2022

This paper proposes using scribbles to annotate LiDAR point clouds and releases ScribbleKITTI, the first scribble-annotated dataset for LiDar semantic segmentation, and presents a pipeline to reduce the performance gap that arises when using such weak annotations.

97 0

Paper Graph

CPGNet: Cascade Point-Grid Fusion Network for Real-Time LiDAR Semantic Segmentation

Xiaoyan Li, Gang Zhang, Hongyu Pan, Zhenhua Wang•Wed Apr 20 2022

CPGNet is proposed, which ensures both effectiveness and efficiency mainly by the following two techniques: the novel Point-Grid (PG) fusion block extracts semantic features mainly on the 2D projected grid for efficiency, while the proposed transformation consistency loss narrows the gap between the single-time model inference and TTA.

38 0

Paper Graph

Point Transformer V3: Simpler, Faster, Stronger

Wanli Ouyang, Xiaoyang Wu, Hengshuang Zhao, Yu Qiao, Li Jiang, Peng-Shuai Wang, Zhijian Liu, Xihui Liu, Tong He•Thu Dec 14 2023

This paper presents Point Transformer V3 (PTv3), which prioritizes simplicity and efficiency over the accuracy of certain mechanisms that are minor to the over-all performance after scaling, such as replacing the precise neighbor search by KNN with an efficient serialized neighbor mapping of point clouds organized with specific patterns.

589 0

Paper Graph

Adding a benchmark result helps the community track progress.