Datasets of Multiple Kinects-based 3D reconstructed meshes

Three different capturing setups are realized, each with 5 Kinects in a circular configuration. The third capturing setup is the one used in the “Huawei/3DLife ACM Multimedia Grand Challenge for 2013” (http://mmv.eecs.qmul.ac.uk/mmgc2013/).

 

For each dataset, two reconstruction methods are considered: A variant of the explicit fusion method described in [1], as well as the volumetric Poisson reconstruction method [2]. The first method runs in real-time (~10 fps). The second one is slower, but produces smooth and watertight reconstructions.

 

The datasets are given as ASCII-PLY files (one for each frame, including vertex positions, normals and colors per vertex). All frames are compressed into a .rar file.

 

[1] D. Alexiadis, D. Zarpalas, P. Daras, “Real-time, full 3-D reconstruction of moving foreground objects from multiple consumer depth cameras”, IEEE Transactions on Multimedia, VOL. 15, NO. 2, pp. 339-358, February 2013

 

[2] M. Kazhdan, M. Bolitho, and H. Hoppe, “Poisson surface reconstruction,” in Proc. of the 4th Eurographics symposium on Geometry processing, SGP ’06, Switzerland, 2006, pp. 61–70.

 

 

 

Details and download

  Name Capturing setup Reconstruction method Number of frames Mean number of vertices per frame Mean number of triangles per frame Download size
1 Skiing3-Zippering.rar 1 [1] 190 ~340 K ~650 K ~ 2.0 GB
2 Skiing3-PoissonLow.rar 1 [2] (maximum tree depth = 8) 190 ~50 K ~100 K ~ 0.4GB
3 Skiing3-PoissonHigh.rar 1 [2] (maximum tree depth = 9) 190 ~ 220 K ~ 450 K ~ 1.0 GB
4 Jogging1-Zippering.rar 1 [1] 231 ~ 290 K ~ 570 K ~ 2.0 GB
5 Jogging1-PoissonLow.rar 1 [2] (maximum tree depth = 8) 231 ~ 50 K ~ 100 K ~ 0.3 GB
6 Jogging1-PoissonHigh.rar 1 [2] (maximum tree depth = 9) 231 ~ 180 K ~ 370 K ~ 1.2GB
7 Dimitris-Zippering.rar 2 [1] 840 ~ 310 K ~ 600 K ~ 8.0 GB
8 Dimitris-PoissonHigh.rar 2 [2] (maximum tree depth = 9) 840 ~ 180 K ~ 360 K ~ 4.4 GB
9 Dimitris2-Zippering.rar 2 [1] 121 ~ 310 K ~ 610 K ~ 1.2 GB
10 Dimitris2-PoissonHigh.rar 2 [2] (maximum tree depth = 9) 121 ~ 190 K ~ 390 K ~ 0.7 GB
11 Alex-Zippering.rar 2 [1] 901 ~ 260 K ~ 510 K ~ 7.5 GB
12 Alex-PoissonHigh.rar 2 [2] (maximum tree depth = 9) 901 ~ 170 K ~ 350 K ~ 4.6 GB
13 Christos-Zippering.rar 2 [1] 762 ~ 270 K ~ 520 K ~ 6.4 GB
14 Christos-PoissonHigh.rar 2 [2] (maximum tree depth = 9) 762 ~ 180 K ~ 360 K ~ 4.0 GB
15 S04_5KW_DimitriosSession4-Zippering.rar 3 [1] 2351 ~ 230 K ~ 440 K ~ 15.0 GB
16 S04_5KW_DimitriosSession4-PoissionLow.rar 3 [2] (maximum tree depth = 8) 2351 ~ 30 K ~ 60 K ~ 2.4 GB
17 S04_5KW_DimitriosSession4-PoissionHigh.rar 3 [2] (maximum tree depth = 9) 2351 ~ 120 K ~ 250 K ~ 9.2 GB
18 S17_5KW_Xenia-Zippering.rar 3 [1] 6531 ~ 190 K ~ 360 K ~ 34.0 GB
19 S17_5KW_Xenia-PoissonLow.rar 3 [2] (maximum tree depth = 8) 6531 ~ 25 K ~ 50 K ~ 7.0 GB
20 S17_5KW_Xenia-PoissonHigh.rar 3 [2] (maximum tree depth = 9) 6531 ~ 170 K ~ 340 K ~ 24.0 GB
Visual Computing Lab

The focus of the Visual Computing Laboratory is to develop new algorithms and architectures for applications in the areas of 3D processing, image/video processing, computer vision, pattern recognition, bioinformatics and medical imaging.

Contact Information

Dr. Petros Daras, Principal Researcher Grade Α
1st km Thermi – Panorama, 57001, Thessaloniki, Greece
P.O.Box: 60361
Tel.: +30 2310 464160 (ext. 156)
Fax: +30 2310 464164
Email: daras@iti.gr