SensatUrban: Learning Semantics from Urban-Scale Photogrammetric Point Clouds

  title={SensatUrban: Learning Semantics from Urban-Scale Photogrammetric Point Clouds},
  author={Qingyong Hu and Bo Yang and Sheikh Khalid and Wen Xiao and Niki Trigoni and A. Markham},
  journal={International Journal of Computer Vision},
  • Qingyong HuBo Yang A. Markham
  • Published 4 January 2022
  • Computer Science, Environmental Science
  • International Journal of Computer Vision
With the recent availability and affordability of commercial depth sensors and 3D scanners, an increasing number of 3D (i.e., RGBD, point cloud) datasets have been publicized to facilitate research in 3D computer vision. However, existing datasets either cover relatively small areas or have limited semantic annotations. Fine-grained understanding of urban-scale 3D scenes is still in its infancy. In this paper, we introduce SensatUrban, an urban-scale UAV photogrammetry point cloud dataset… 

UrbanBIS: a Large-scale Benchmark for Fine-grained Urban Building Instance Segmentation

In addition to the carefully-annotated point clouds, UrbanBIS provides high-resolution aerial-acquisition photos and high-quality large-scale 3D reconstruction models, which shall facilitate a wide range of studies such as multi-view stereo, urban LOD generation, aerial path planning, autonomous navigation, road network extraction, and so on.

STPLS3D: A Large-Scale Synthetic and Real Aerial Photogrammetry 3D Point Cloud Dataset

A synthetic aerial photogrammetry point clouds generation pipeline that takes full advantage of open geospatial data sources and off-the-shelf commercial packages is introduced that simulates the reconstruction process of the real environment by following the same UAV flight pattern on different synthetic terrain shapes and building densities.

Meta-RangeSeg: LiDAR Sequence Semantic Segmentation Using Multiple Feature Aggregation

This work proposes a novel approach to semantic segmentation for LiDAR sequences named Meta-RangeSeg, where a new range residual image representation is introduced to capture the spatial-temporal information and Meta-Kernel is employed to extract the meta features.

Small but Mighty: Enhancing 3D Point Clouds Semantic Segmentation with U-Next Framework

This paper proposes U-Next, a small but mighty framework designed for point cloud semantic segmentation that shows consistent and visible performance improvements across different tasks and baseline models, indicating its great potential to serve as a general framework for future research.

Benchmarking the Robustness of LiDAR Semantic Segmentation Models

A robust LiDAR segmentation model (RLSeg) is designed which greatly boosts the robustness ofLiDAR semantic segmentation models under various corruptions with simple but effective modifications.

Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Clouds

This paper proposes a highly-efficient single-stage point-based 3D detector, termed IA-SSD, that achieves a superior speed of 80+ frames-per-second on the KITTI dataset with a single RTX2080Ti GPU.

3D point cloud reconstruction and segmentation for large scene based on UAV aerial images

  • Zhen ChenLu Lou
  • Computer Science, Environmental Science
    Other Conferences
  • 2022
A point cloud reconstruction and segmentation method which use the improved MVSNet to reconstruct the UAV aerial image, and then the generated point cloud is segmented by using the RandLA-Net model to meet the needs of the smart city and provides new technical references for 3D digital city modeling.

TerrainMesh: Metric-Semantic Terrain Reconstruction from Aerial Images Using Joint 2D-3D Learning

Quantitative and qualitative evaluation using real aerial images show the potential of the joint 2D-3D learning approach to reconstruct a local metric-semantic mesh at each camera keyframe maintained by a visual odometry algorithm to support environmental monitoring and surveillance applications.

3DAC: Learning Attribute Compression for Point Clouds

A deep compression network is introduced, termed 3DAC, to explicitly compress the attributes of 3D point clouds and reduce storage usage by proposing a deep entropy model to model the probabilities of these coefficients by considering information hidden in attribute transforms and previous encoded attributes.

EarthNets: Empowering AI in Earth Observation

A comprehensive review of more than 400 publicly published datasets, including applications like land use/cover, change/disaster monitoring, scene understanding, agriculture, climate change, and weather forecasting, to build a new benchmark for model evaluation of deep learning methods on remote sensing data.

Towards Semantic Segmentation of Urban-Scale 3D Point Clouds: A Dataset, Benchmarks and Challenges

This paper presents an urban-scale photogrammetric point cloud dataset with nearly three billion richly annotated points, which is three times the number of labeled points than the existing largest photogrammatric point clouds dataset.

Toronto-3D: A Large-scale Mobile LiDAR Dataset for Semantic Segmentation of Urban Roadways

  • W. TanNannan Qin Jonathan Li
  • Environmental Science, Computer Science
    2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
  • 2020
Toronto-3D is introduced, a large-scale urban outdoor point cloud dataset acquired by a MLS system in Toronto, Canada for semantic segmentation and the capability of this dataset to train deep learning models effectively is confirmed.

LASDU: A Large-Scale Aerial LiDAR Dataset for Semantic Labeling in Dense Urban Areas

This work presents a large-scale aerial LiDAR point cloud dataset acquired in a highly-dense and complex urban area and includes more than three million points with five classes of objects labeled, serving as a benchmark for assessing semantic labeling methods.

CSPC-Dataset: New LiDAR Point Cloud Dataset and Benchmark for Large-Scale Scene Semantic Segmentation

A new point cloud dataset, namely CSPC-Dataset (Complex Scene Point Cloud Dataset) for large-scale scene semantic segmentation is constructed and a new benchmark is constructed, which includes approximately 68 million points with explicit semantic labels.

SemanticKITTI: A Dataset for Semantic Scene Understanding of LiDAR Sequences

A large dataset to propel research on laser-based semantic segmentation, which opens the door for the development of more advanced methods, but also provides plentiful data to investigate new research directions.


A new annotated 3D dataset which is unique in three ways and depicts the village of Hessigheim (Germany), henceforth referred to as H3D, designed for promoting research in the field of 3D data analysis and to evaluate and rank existing and emerging approaches for semantic segmentation of both data modalities.

DALES: A Large-scale Aerial LiDAR Data Set for Semantic Segmentation

The nature of the data, annotation workflow, and benchmark of current state-of-the-art algorithm performance on the DALES data set are described, and a critical number of expert verified hand-labeled points for the evaluation of new 3D deep learning algorithms are given.

SalsaNet: Fast Road and Vehicle Segmentation in LiDAR Point Clouds for Autonomous Driving

This paper introduces a deep encoder-decoder network, named SalsaNet, for efficient semantic segmentation of 3D LiDar point clouds, and introduces an auto-labeling process which transfers automatically generated labels from the camera to LiDAR.

SemanticPOSS: A Point Cloud Dataset with Large Quantity of Dynamic Instances

Experimental results show that SemanticPOSS can help to improve the prediction accuracy of dynamic objects as people, car in some degree and the data is collected in Peking University and uses the same data format as SemanticKITTI. A new Large-scale Point Cloud Classification Benchmark

It is hoped this http URL will pave the way for deep learning methods in 3D point cloud labelling to learn richer, more general 3D representations, and first submissions after only a few months indicate that this might indeed be the case.