Multi-View Three-Dimensional Reconstruction of Weak Texture Regions Based on Simple Lidar

Tingya Liang; Xie Han; Haoyang Li

doi:10.3788/LOP241885

Laser & Optoelectronics Progress, Volume. 62, Issue 8, 0828002(2025)

Multi-View Three-Dimensional Reconstruction of Weak Texture Regions Based on Simple Lidar

Tingya Liang^1,2,3、*, Xie Han^1,2,3, and Haoyang Li^1,2,3

Author Affiliations

¹School of Computer Science and Technology, North University of China, Taiyuan 030051, Shanxi , China

²Shanxi Provincial Key Laboratory of Machine Vision and Virtual Reality, Taiyuan 030051, Shanxi , China

³Shanxi Province's Vision Information Processing and Intelligent Robot Engineering Research Center, Taiyuan 030051, Shanxi , China

show less

Abstract Get PDF(in Chinese)

Figures & Tables(10)

Fig. 1. Algorithm network flowchart

Download full size

Fig. 2. Depth statistics histogram. (a) (c) Original depth value; (b) (d) depth value for noise cancellation

Download full size

Fig. 3. Lidar and phone camera calibration

Download full size

Fig. 4. Depth map comparison. (a) Sparse point cloud; (b) enhanced point cloud

Download full size

Fig. 5. RGB image edge detection. (a) RGB image; (b) Canny edge detection; (c) bf-Canny edge detection

Download full size

Fig. 6. MVS result

Download full size

Fig. 7. Reconstruction result

Download full size

Table 1. Experimental environment information

View table

Table 1. Experimental environment information

Type	Version or model
Oerating system	Windows 11
Central processing unit	Intel Core i7-12700
Graphics processing unit	NVIDIA GeForce RTX 3060
MATLAB	MATLAB R2022b
VeloView	VeloView 3.5.0
COLMAP	Colmap 3.9.1
Lidar	Velodyne VLP-16
Phonecam	Vivo iqoo-8
Lidar scanner	FARO Focus

Table 2. Quantitative analysis of the same scene
View table
Table 2. Quantitative analysis of the same scene
Method Year Number of point clouds Chamfer distance
COLMAP^［2］ 2016 532510 0.48
CasMVSNet^［7］ 2020 2149126 0.43
RcMVSNet^［23］ 2022 2996352 0.47
GeoMVSNet^［9］ 2023 6732912 0.40
Ours — 13643396 0.31

Table 3. Ablation experiment

View table

Table 3. Ablation experiment

Input	GeoMVSNet	Consistency calibration of lidar data	Lidar depth map enhancement algorithm	Chamfer distance
Image	√	—	—	0.40
Image+lidar	√	—	—	0.41
Image+lidar	√	√	—	0.38
Image+lidar	√	—	√	0.47
Image+lidar	√	√	√	0.31

Tools

Get Citation

Copy Citation Text

Tingya Liang, Xie Han, Haoyang Li. Multi-View Three-Dimensional Reconstruction of Weak Texture Regions Based on Simple Lidar[J]. Laser & Optoelectronics Progress, 2025, 62(8): 0828002

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites