Institut für Kognitionswissenschaft

Institute of Cognitive Science


Osnabrück University navigation and search


Main content

Top content

Evaluation of multi-view 3D reconstruction software - CAIP2015

A number of software solutions for reconstructing 3D models from multi-view image sets have been released in recent years. Based on an unordered collection of photographs, most of these solutions extract 3D models using structure-from-motion (SFM) algoritdms. In this work, we compare the resulting 3D models qualitatively and quantitatively. To achieve these objectives, we have developed different metdods of comparison for all software solutions. We discuss the perfomance and existing drawbacks. Particular attention is paid to the ability to create printable 3D models or 3D models usable for other applications.

On this page we present additional material regarding our paper Evaluation of multi-view 3D reconstruction software [1] in the proceedings of the 16th International Conference on Computer Analysis of Images and Patterns (CAIP'15). To view the 3D point clouds please click on the corresponding image.

Additional Material (click on the images)

Data set PhotoScan 123D Catch VisualSFM ARC 3D Ground Truth
P11 fountain-P11 fountain-P11: PhotoScan fountain-P11: 123DCatch fountain-P11: VisualSFM fountain-P11: ARC 3D fountain-P11: Ground Truth
P8 Herz-Jesu-P8 Herz-Jesu-P8: PhotoScan Herz-Jesu-P8: 123D Catch Herz-Jesu-P8: VisualSFM Herz-Jesu-P8:ARC 3D Herz-Jesu-P8: Ground Truth
Oxford Dinosaur Oxford Dinosaur Oxford Dinosaur: PhotoScan Oxford Dinosaur: 123D Catch Oxford Dinosaur: VisualSFM N/A Oxford Dinosaur: Ground Truth
Oxford Dinosaur* Oxford Dinosaur Oxford Dinosaur: PhotoScan Oxford Dinosaur: 123D Catch Oxford Dinosaur: VisualSFM N/A Oxford Dinosaur: Ground Truth

Created 3D models of PhotoScan, 123D Catch, VisualSFM and ARC 3D on four data sets: fountain-P11 (11 images), Herz-Jesu-P8 (8 images), Oxford Dinosaur (36 images) and *Oxford Dinosaur with removed background (36 images). One sample image of each data set is shown on the left, reconstruction results of each tool are shown in the center and the corresponding ground truths are shown on the right.

Heat Maps (click on the images)

Result fountain-P11: PhotoScan

(a)

Result fountain-P11: 123D Catch

(b)

Result fountain-P11: VisualSFM

(c)

Result fountain-P11: ARC_3D

(d)

Heat map of the minimal distance between the ground truth point cloud and the triangular mesh of the created model as reference on the fountain-P11 data set. Points with distance differences more than ±0.1 are not visualized; distance differences between -0,05 and 0.05 are colorized in the scheme blue-green-red. On the right next to the legend, the distance distribution is shown. Models are created by (a) PhotoScan, (b) 123D Catch, (c) VisualSFM and (d) ARC 3D.

Result Herz-Jesu-P8: PhotoScan

(a)

Result Herz-Jesu-P8: 123D Catch

(b)

Result Herz-Jesu-P8: VisualSFM

(c)

Result Herz-Jesu-P8: ARC 3D

(d)

Heat map of the minimal distance between the ground truth point cloud and the triangular mesh of the created model as reference on the Herz-Jesu-P8 data set. Points with distance differences more than ±0.1 are not visualized; distance differences between -0,05 and 0.05 are colorized in the scheme blue-green-red. On the right next to the legend, the distance distribution is shown. Models are created by (a) PhotoScan, (b) 123D Catch, (c) VisualSFM and (d) ARC 3D.

Result Oxford Dinosaur: PhotoScan

(a)

Result Oxford Dinosaur: 123D Catch

(b)

Result Oxford Dinosaur: VisualSFM

(c)

Result Oxford Dinosaur: PhotoScan

(d)

Result Oxford Dinosaur: 123D Catch

(e)

Result Oxford Dinosaur: VisualSFM

(f)

Heat map of the minimal distance between the ground truth point cloud and the triangular mesh of the created model as reference on the original Oxford Dinosaur data set (a)-(c) and on Oxford Dinosaur with removed background (d)-(f). Points with distance differences more than ±0.01 are not visualized; distance differences between -0.005 and 0.005 are colorized in the scheme blue-green-red. On the right next to the legend, the distance distribution is shown. Models are created by (a),(d) PhotoScan, (b),(e) 123D Catch and (c),(f) VisualSFM.

References

[1] J. Schöning & G. Heidemann.
Evaluation of Multi-view 3D Reconstruction Software.<br/>In Computer Analysis of Images and Patterns, 9257 : 450-461, ISBN: 978-3-319-23116-7, 2015. Springer International Publishing.
| PDF | DOI | URL | BibTeX