MPI FAUST Dataset

Results and Rankings

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


Intra-subject challenge
Average error
SP_intra_challenge [1] 1.568 Visualize Results
Convex-Opt [2] 4.86 Visualize Results
CHARM [3] 15.157 Visualize Results
FMNet [4] 2.436 Visualize Results
FARM [5] 2.81 Visualize Results
3D-CODED : 3D Correspondences by Deep Deformation [6] 1.985 Visualize Results
LBS-AE (Unsupervised) [7] 2.161 Visualize Results
Unsupervised Learning of Dense Shape Correspondence [8] 2.51 Visualize Results
Unsupervised Learning of Dense Shape Correspondence [9] 2.818 Visualize Results
unsupervised 3D-CODED : 3D Correspondences by Deep Deformation [10] 2.789 Visualize Results
BPS [11] 2.327 Visualize Results
Learning elementary structures for 3D shape generation and matching [12] 1.626 Visualize Results
Unsupervised Cyclic mapper intra [13] 2.12 Visualize Results
JOMS-intra-female [14] 2.353 Visualize Results
george intra [15] 6.737 Visualize Results
2icp [16] 6.724 Visualize Results
test-2icp-2refine [17] 12.746 Visualize Results
combine-test [18] 10.158 Visualize Results
Reproduce FMNet [19] 10.885 Visualize Results
reproduce UFMNet [20] 5.153 Visualize Results
fixed mesh [21] 4.531 Visualize Results
reproduce UFMNet 1 [22] 12.079 Visualize Results
reproduce UFMNet 2 [23] 12.053 Visualize Results
DHNN_ours2 [24] 1.369 Visualize Results
DHNN_ours1 [25] 1.395 Visualize Results
DHNN_ours_e1 [26] 1.17 Visualize Results
DHNN_ours_e2 [27] 1.011 Visualize Results
Intra Test Fr [28] 2.256 Visualize Results
Intra Test FT2 LR Fr [29] 2.251 Visualize Results
JOMS-intra-unisex [30] 2.304 Visualize Results
JOMS-intra-male [31] 2.387 Visualize Results
JOMS-intra-combined [32] 2.301 Visualize Results
Adversarial GP Network [33] 1.904 Visualize Results
UD^2E-Net [34] 1.512 Visualize Results
Deep Virtual Marker (multi-view) [35] 1.185 Visualize Results
Deep Virtual Marker (one-shot) [36] 1.417 Visualize Results
Faust-3 [37] 26.903 Visualize Results
Faust-7 [38] 22.1 Visualize Results
PGMNet [39] 0.997 Visualize Results
Test-3D [40] 1.759 Visualize Results
led_intra [41] 1.93 Visualize Results
Faust3+GLASS(2858) [42] 13.18 Visualize Results
Faust7+GLASS(3573) [43] 11.78 Visualize Results
SMPL650+GLASS (84k) [44] 6.856 Visualize Results
SMPL650+GLASS (192k) [45] 6.922 Visualize Results
SMPL650 [46] 14.595 Visualize Results
synorim (pairwise) [47] 1.486 Visualize Results
References
[1]
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.
[2]
Convex-Opt
Robust Nonrigid Registration by Convex Optimization. Qifeng Chen, Vladlen Koltun. International Conference on Computer Vision (ICCV), 2015
[3]
CHARM
[4]
FMNet
"Deep functional maps: Structured prediction for dense shape correspondence". Litany, Remez, Rodola, Bronstein, Bronstein. Proc. ICCV 2017
[5]
FARM
"FARM: Functional Automatic Registration Method for 3D Human Bodies". Marin, Melzi, Rodola, Castellani. arXiv:1807.10517, 2018.
[6]
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.
[7]
LBS-AE (Unsupervised)
LBS Autoencoder: Self-supervised Fitting of Articulated Meshes to Point Clouds, CVPR 2019
[8]
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)
[9]
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)
[10]
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.
[11]
BPS
Efficient Learning on Point Clouds with Basis Point Sets
[12]
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
[13]
Unsupervised Cyclic mapper intra
Cyclic Functional Mapping: Self-supervised correspondence between non-isometric deformable shapes
[14]
JOMS-intra-female
Anonymous.
[15]
george intra
[16]
2icp
[17]
test-2icp-2refine
[18]
combine-test
[19]
Reproduce FMNet
[20]
reproduce UFMNet
[21]
fixed mesh
Use unsurpervised loss. 0, true, 0 fixed meshes
[22]
reproduce UFMNet 1
with 10, true, 10 Oshri data
[23]
reproduce UFMNet 2
20, true, 20 Oshri data
[24]
DHNN_ours2
Disentangled Human Body Embedding Based on Deep Hierarchical Neural Network. IEEE TVCG 2020
[25]
DHNN_ours1
Disentangled Human Body Embedding Based on Deep Hierarchical Neural Network. IEEE TVCG 2020
[26]
DHNN_ours_e1
Disentangled Human Body Embedding Based on Deep Hierarchical Neural Network. IEEE TVCG 2020
[27]
DHNN_ours_e2
Disentangled Human Body Embedding Based on Deep Hierarchical Neural Network. IEEE TVCG 2020
[28]
Intra Test Fr
Anonymous.
[29]
Intra Test FT2 LR Fr
Anonymous.
[30]
JOMS-intra-unisex
Anonymous.
[31]
JOMS-intra-male
Anonymous.
[32]
JOMS-intra-combined
Anonymous.
[33]
Adversarial GP Network
Reconstructing human body mesh from point clouds by adversarial GP network, ACCV2020
[34]
UD^2E-Net
Unsupervised Dense Deformation Embedding Network for Template-free Shape Correspondence, ICCV2021
[35]
Deep Virtual Marker (multi-view)
Deep Virtual Markers for Articulated 3D Shapes. ICCV 2021
[36]
Deep Virtual Marker (one-shot)
Deep Virtual Markers for Articulated 3D Shapes. ICCV 2021
[37]
Faust-3
Anonymous.
[38]
Faust-7
Anonymous.
[39]
PGMNet
Anonymous.
[40]
Test-3D
Anonymous.
[41]
led_intra
Anonymous.
[42]
Faust3+GLASS(2858)
Anonymous.
[43]
Faust7+GLASS(3573)
Anonymous.
[44]
SMPL650+GLASS (84k)
Anonymous.
[45]
SMPL650+GLASS (192k)
Anonymous.
[46]
SMPL650
Anonymous.
[47]
synorim (pairwise)
Anonymous.