Here: Home >  benchmark




Deep learning-based methods have become the de-facto baseline for image registration task in the field of computer vision, but due to the lack of large benchmark datasets, they have not yet led to a true milestone for 3D point cloud registration. The large-scale benchmark datasets would promote the benchmarking of state-of-the-art algorithms in this field, and provide better comparisons and insights into the advantages and disadvantages of different registration methods on a common base.


WHU-TLS benchmark dataset

The proposed the benchmark dataset consists of 115 scans and in total over 1740 million 3D points collected from 11 different environments (i.e., subway station, high-speed railway platform, mountain, forest, park, campus, residence, riverbank, heritage building, underground excavation and tunnel) with varying point density, clutter, and occlusion. The ground-truth transformations, the transformations calculated by Dong et. al. (2018)and the registration graphs are also provided for researchers, which aims to yield better comparisons and insights into the strengths and weaknesses of different registration approaches on a common base. We hope the benchmark meets the needs of the research community and becomes an important dataset for the development of cutting-edge TLS point cloud registration methods. In addition, the proposed benchmark also provides suitable datasets for the applications of safe railway operation, river survey and regulation, forest structure assessment, cultural heritage conservation, landslide monitoring and underground asset management. The benchmark data sets are shown in Fig.1. Table 1 shows the detailed descriptions of the WHU-TLS data sets in terms of the data acquisition equipment, number of scans, number of points, range covered, organization of the environment, location of the environment, and the minimum and maximum overlaps between pairwise point clouds.

(a) WHU-TLS Subway station

(b) WHU-TLS Railway

(c) WHU-TLS Mountain

(d) FGI-Forest 

(e) WHU-TLS   Park

(f) WHU-TLS   Campus

(g) WHU-TLS   Residence

(h) WHU-TLS   River bank

(i) WHU-TLS   Heritage building

(j) WHU-TLS   Excavation

(k) WHU-TLS   Tunnel

Fig. 1 The WHU-TLS data set  

Table 2. Details of the WHU-TLS benchmark data set

NameScanner#Scans#Pts(million)Overlap (%)
WHU-TLS Subway stationIMAGER 5010C6237.5723.764.3
WHU-TLS RailwayVZ-400849.8610.966.1
WHU-TLS MountainScanStation C5619.6113.442.3
FGI-ForestLeica   HDS61005149.4534.655.5
WHU-TLS ParkVZ-40032160.2424.482.8
WHU-TLS CampusVZ-40010109.055.649.6
WHU-TLS ResidenceLeica P40743.701.091.4
WHU-TLS River bankVZ-4001393.1122.649.6
WHU-TLS Heritage buildingVZ-4009238.1628.769.4
WHU-TLS ExcavationVZ-40012482.429.072.8
WHU-TLS TunnelVZ-4007157.025.5032.0

Data requests

Please fill out this Data Request if you have access to google forms.

If not, please fill out this one (alternative link for Chinese users).

Download links will be sent automatically after completing the application.



This dataset is available under the Creative Commons Attribution Non-Commercial No Derivatives License CC-BY-NC-ND-3.0 . Whenever this dataset is involved, the user of this dataset :

Provide the dataset title : "WHU-TLS dataset"

Cite the following journal paper :

Dong Z., Yang B., Liang F., Huang R., & Scherer S., 2018. Hierarchical registration of unordered TLS point clouds based on binary shape context descriptor. ISPRS J. Photogramm. Remote Sens. 144, 61-79.

Dong Z., Liang F., Yang B., Xu Y., Zang Y., Li J., Wang Y., Dai W., Fan H., Hyyppä J., Stilla U., 2020. Registration of large-scale TLS Point Clouds: A Review and Benchmark. ISPRS J. Photogramm. Remote Sens. 163, 327-342.


Contact us


In order to give some feedback about the “WHU-TLS” benchmark dataset, please contact:

Chong Liu

State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing,

Wuhan University, Wuhan, China, 430079.

For detailed information, please see