Visual Results by Method

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





  • Intra
  • 00_corr_final
  • 01_corr_final
  • 02_corr_final
  • 03_corr_final
  • 04_corr_final
  • 05_corr_final
  • 06_corr_final
  • 07_corr_final
  • 08_corr_final
  • 09_corr_final
  • 10_corr_final
  • 11_corr_final
  • 12_corr_final
  • 13_corr_final
  • 14_corr_final
  • 15_corr_final
  • 16_corr_final
  • 17_corr_final
  • 18_corr_final
  • 19_corr_final
  • 20_corr_final
  • 21_corr_final
  • 22_corr_final
  • 23_corr_final
  • 24_corr_final
  • 25_corr_final
  • 26_corr_final
  • 27_corr_final
  • 28_corr_final
  • 29_corr_final
  • 30_corr_final
  • 31_corr_final
  • 32_corr_final
  • 33_corr_final
  • 34_corr_final
  • 35_corr_final
  • 36_corr_final
  • 37_corr_final
  • 38_corr_final
  • 39_corr_final
  • 40_corr_final
  • 41_corr_final
  • 42_corr_final
  • 43_corr_final
  • 44_corr_final
  • 45_corr_final
  • 46_corr_final
  • 47_corr_final
  • 48_corr_final
  • 49_corr_final
  • 50_corr_final
  • 51_corr_final
  • 52_corr_final
  • 53_corr_final
  • 54_corr_final
  • 55_corr_final
  • 56_corr_final
  • 57_corr_final
  • 58_corr_final
  • 59_corr_final

Metrics


Average error
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]
JOMS-inter-combined
Anonymous.
[2]
JOMS-inter-unisex
Anonymous.
[3]
2icp
[4]
3D-CODED : 3D Correspondences by Deep Deformation
3D-CODED : 3D Correspondences by Deep Deformation, Groueix, Thibault and Fisher, Matthew and Kim, Vladimir G. and Russell, Bryan and Aubry, Mathieu, ECCV 2018.
[5]
Adversarial GP Network
Reconstructing human body mesh from point clouds by adversarial GP network, ACCV2020
[6]
Anonymous
Anonymous.
[7]
BPS
Efficient Learning on Point Clouds with Basis Point Sets
[8]
CHARM
[9]
combine-test
[10]
Convex-Opt
Robust Nonrigid Registration by Convex Optimization. Qifeng Chen, Vladlen Koltun. International Conference on Computer Vision (ICCV), 2015
[11]
Deep Virtual Marker (multi-view)
Deep Virtual Markers for Articulated 3D Shapes. ICCV 2021
[12]
Deep Virtual Marker (one-shot)
Deep Virtual Markers for Articulated 3D Shapes. ICCV 2021
[13]
DHNN_ours_e1
Disentangled Human Body Embedding Based on Deep Hierarchical Neural Network. IEEE TVCG 2020
[14]
DHNN_ours_e2
Disentangled Human Body Embedding Based on Deep Hierarchical Neural Network. IEEE TVCG 2020
[15]
DHNN_ours1
Disentangled Human Body Embedding Based on Deep Hierarchical Neural Network. IEEE TVCG 2020
[16]
DHNN_ours2
Disentangled Human Body Embedding Based on Deep Hierarchical Neural Network. IEEE TVCG 2020
[17]
FARM
"FARM: Functional Automatic Registration Method for 3D Human Bodies". Marin, Melzi, Rodola, Castellani. arXiv:1807.10517, 2018.
[18]
Faust-3
Anonymous.
[19]
Faust-7
Anonymous.
[20]
Faust3+GLASS(2858)
Anonymous.
[21]
Faust3+GLASS(2858)
Anonymous.
[22]
Faust3+GLASS(2858)
Anonymous.
[23]
Faust3+GLASS(2858)
Anonymous.
[24]
Faust3+GLASS(2858)
Anonymous.
[25]
Faust3+GLASS(2858)
Anonymous.
[26]
Faust3+GLASS(2858)
Anonymous.
[27]
Faust7+GLASS(3573)
Anonymous.
[28]
Faust7+GLASS(3573)
Anonymous.
[29]
Faust7+GLASS(3573)
Anonymous.
[30]
fixed mesh
Use unsurpervised loss. 0, true, 0 fixed meshes
[31]
FMNet
"Deep functional maps: Structured prediction for dense shape correspondence". Litany, Remez, Rodola, Bronstein, Bronstein. Proc. ICCV 2017
[32]
george intra
[33]
george_test_folder
Anonymous.
[34]
george_test_folder
Anonymous.
[35]
george_test_folder
Anonymous.
[36]
george_test_folder
Anonymous.
[37]
george_test_folder
Anonymous.
[38]
george_test_folder
Anonymous.
[39]
h_inter_initial
Anonymous.
[40]
Inter Test FT2 LR Fr
Anonymous.
[41]
Inter Test FT2 LR Fr
Anonymous.
[42]
Intra Test Fr
Anonymous.
[43]
Intra Test Fr
Anonymous.
[44]
Intra Test Fr
Anonymous.
[45]
Intra Test FT2 LR Fr
Anonymous.
[46]
JOMS-inter-female
Anonymous.
[47]
JOMS-inter-male
Anonymous.
[48]
JOMS-intra-combined
Anonymous.
[49]
JOMS-intra-female
Anonymous.
[50]
JOMS-intra-male
Anonymous.
[51]
JOMS-intra-unisex
Anonymous.
[52]
LBS-AE (Unsupervised)
LBS Autoencoder: Self-supervised Fitting of Articulated Meshes to Point Clouds, CVPR 2019
[53]
Learning elementary structures for 3D shape generation and matching
Learning elementary structures for 3D shape generation and matching, Deprelle, Theo, Groueix, Thibault and Fisher, Matthew and Kim, Vladimir G. and Russell, Bryan and Aubry, Mathieu, ECCV 2018
[54]
Learning Shape Spaces via on-the-fly Correspondence Estimation
Anonymous. INTER
[55]
Learning Shape Spaces via on-the-fly Correspondence Estimation
Anonymous. INTRA
[56]
led_inter
Anonymous.
[57]
led_intra
Anonymous.
[58]
LoopReg
LoopReg: Self-supervised Learning of Implicit Surface Correspondences, Pose and Shape for 3D Human Mesh Registration, NeurIPS 2020 (oral)
[59]
mp_inter_final
Anonymous.
[60]
myaugreo
Anonymous.
[61]
PGMNet
Anonymous.
[62]
PGMNet_Inter
Anonymous.
[63]
Reproduce FMNet
[64]
reproduce UFMNet
[65]
reproduce UFMNet 1
with 10, true, 10 Oshri data
[66]
reproduce UFMNet 2
20, true, 20 Oshri data
[67]
SMPL650
Anonymous.
[68]
SMPL650
Anonymous.
[69]
SMPL650
Anonymous.
[70]
SMPL650+GLASS (192k)
Anonymous.
[71]
SMPL650+GLASS (192k)
Anonymous.
[72]
SMPL650+GLASS (84k)
Anonymous.
[73]
SMPL650+GLASS (84k)
Anonymous.
[74]
SP_intra_challenge
S. Zuffi, M. J. Black, "The Stitched Puppet: A Graphical Model of 3D Human Shape and Pose", CVPR, Boston, MA, June 2015.
[75]
synorim (pairwise)
Anonymous.
[76]
test-2icp-2refine
[77]
Test-3D
Anonymous.
[78]
Test-3D
Anonymous.
[79]
try_inter
Anonymous.
[80]
try_inter
Anonymous.
[81]
UD^2E-Net
Unsupervised Dense Deformation Embedding Network for Template-free Shape Correspondence, ICCV2021
[82]
unsupervised 3D-CODED : 3D Correspondences by Deep Deformation
3D-CODED : 3D Correspondences by Deep Deformation, Groueix, Thibault and Fisher, Matthew and Kim, Vladimir G. and Russell, Bryan and Aubry, Mathieu, ECCV 2018.
[83]
Unsupervised Cyclic mapper intra
Cyclic Functional Mapping: Self-supervised correspondence between non-isometric deformable shapes
[84]
Unsupervised Learning of Dense Shape Correspondence
Unsupervised Learning of Dense Shape Correspondence, Oshri Halimi, Or Litany, Emanuele Rodola, Alex M. Bronstein, Ron Kimmel; (CVPR 2019)
[85]
Unsupervised Learning of Dense Shape Correspondence
Unsupervised Learning of Dense Shape Correspondence, Oshri Halimi, Or Litany, Emanuele Rodola, Alex M. Bronstein, Ron Kimmel; (CVPR 2019)