Visual Results by Method

Results for methods appear here after users upload them and approve them for public display.





  • Final_plot_final All pairs, Average error = 8.304
  • 00_worse_final Pair 00, Average error = 4.698
  • 01_worse_final Pair 01, Average error = 4.800
  • 02_worse_final Pair 02, Average error = 5.950
  • 03_worse_final Pair 03, Average error = 26.802
  • 04_worse_final Pair 04, Average error = 19.077
  • 05_worse_final Pair 05, Average error = 3.910
  • 06_worse_final Pair 06, Average error = 6.005
  • 07_worse_final Pair 07, Average error = 25.036
  • 08_worse_final Pair 08, Average error = 6.511
  • 09_worse_final Pair 09, Average error = 7.370
  • 10_worse_final Pair 10, Average error = 25.874
  • 11_worse_final Pair 11, Average error = 12.254
  • 12_worse_final Pair 12, Average error = 5.921
  • 13_worse_final Pair 13, Average error = 4.533
  • 14_worse_final Pair 14, Average error = 10.973
  • 15_worse_final Pair 15, Average error = 11.496
  • 16_worse_final Pair 16, Average error = 7.644
  • 17_worse_final Pair 17, Average error = 4.261
  • 18_worse_final Pair 18, Average error = 5.566
  • 19_worse_final Pair 19, Average error = 4.989
  • 20_worse_final Pair 20, Average error = 4.869
  • 21_worse_final Pair 21, Average error = 5.373
  • 22_worse_final Pair 22, Average error = 6.443
  • 23_worse_final Pair 23, Average error = 6.408
  • 24_worse_final Pair 24, Average error = 3.474
  • 25_worse_final Pair 25, Average error = 13.287
  • 26_worse_final Pair 26, Average error = 4.470
  • 27_worse_final Pair 27, Average error = 6.948
  • 28_worse_final Pair 28, Average error = 7.083
  • 29_worse_final Pair 29, Average error = 4.910
  • 30_worse_final Pair 30, Average error = 4.554
  • 31_worse_final Pair 31, Average error = 4.944
  • 32_worse_final Pair 32, Average error = 19.117
  • 33_worse_final Pair 33, Average error = 3.391
  • 34_worse_final Pair 34, Average error = 2.650
  • 35_worse_final Pair 35, Average error = 3.275
  • 36_worse_final Pair 36, Average error = 10.118
  • 37_worse_final Pair 37, Average error = 10.939
  • 38_worse_final Pair 38, Average error = 4.820
  • 39_worse_final Pair 39, Average error = 9.976

Metrics


Average error Average error over all the ground-truth correspondences.
Error visualization: for each pair, the plot on the left reports the errors in cm for all the ground-truth correspondences (sorted by decreasing error).

For the intra-subject challenge, the figure on the right shows the error distribution over the vertices of the first scan in the pair (blue represents the minimum error, red represents the maximum error).

For the inter-subject challenge, the figure on the right shows the error distribution over different areas of the first scan in the pair (each area corresponds to a landmark location; black represents the minimum error, white represents the maximum error).


References
[1]
Convex-Opt
Robust Nonrigid Registration by Convex Optimization. Qifeng Chen, Vladlen Koltun. International Conference on Computer Vision (ICCV), 2015
[2]
SP_inter_challenge
S. Zuffi, M. J. Black, "The Stitched Puppet: A Graphical Model of 3D Human Shape and Pose", CVPR, Boston, MA, June 2015.