MPI FAUST Dataset

Results and Rankings

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


Inter-subject challenge
Average error
SP_inter_challenge [1] 3.126 Visualize Results
Convex-Opt [2] 8.304 Visualize Results
FMNet [3] 4.826 Visualize Results
FARM [4] 4.123 Visualize Results
3D-CODED : 3D Correspondences by Deep Deformation [5] 2.878 Visualize Results
unsupervised 3D-CODED : 3D Correspondences by Deep Deformation [6] 4.883 Visualize Results
LBS-AE (Unsupervised) [7] 4.079 Visualize Results
BPS [8] 4.529 Visualize Results
Smooth Shells [9] 3.929 Visualize Results
Learning elementary structures for 3D shape generation and matching [10] 2.578 Visualize Results
Unsupervised Cyclic mapper inter [11] 4.068 Visualize Results
JOMS-inter-female [12] 3.234 Visualize Results
DHNN_ours2 [13] 2.222 Visualize Results
DHNN_ours1 [14] 2.266 Visualize Results
DHNN_ours_e1 [15] 2.521 Visualize Results
DHNN_ours_e2 [16] 1.992 Visualize Results
LSA-Conv: Learning localneighboring structure for robust 3d shape representation [17] 2.501 Visualize Results
Inter Test Fr [18] 2.974 Visualize Results
Inter Test FT2 LR Fr [19] 3.033 Visualize Results
JOMS-inter-unisex [20] 3.525 Visualize Results
JOMS-inter-male [21] 3.519 Visualize Results
JOMS-inter-combined [22] 3.422 Visualize Results
LoopReg [23] 2.66 Visualize Results
Adversarial GP network [24] 2.759 Visualize Results
try_inter [25] 33.439 Visualize Results
UD^2E-Net-Inter [26] 3.086 Visualize Results
PAI_GCN [27] 12.112 Visualize Results
Deep Virtual Marker (multi-view) [28] 2.372 Visualize Results
Deep Virtual Marker (one-shot) [29] 2.495 Visualize Results
PGMNet_Inter [30] 2.238 Visualize Results
Anonymous [31] 6.78 Visualize Results
Test-3D [32] 2.673 Visualize Results
mp_inter_final [33] 14.47 Visualize Results
h_inter_initial [34] 25.024 Visualize Results
led_inter [35] 2.824 Visualize Results
myaugreo [36] 12.849 Visualize Results
Learning Shape Spaces via on-the-fly Correspondence Estimation [37] 17.051 Visualize Results
References
[1]
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.
[2]
Convex-Opt
Robust Nonrigid Registration by Convex Optimization. Qifeng Chen, Vladlen Koltun. International Conference on Computer Vision (ICCV), 2015
[3]
FMNet
"Deep functional maps: Structured prediction for dense shape correspondence". Litany, Remez, Rodola, Bronstein, Bronstein. Proc. ICCV 2017
[4]
FARM
"FARM: Functional Automatic Registration Method for 3D Human Bodies". Marin, Melzi, Rodola, Castellani. arXiv:1807.10517, 2018.
[5]
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.
[6]
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.
[7]
LBS-AE (Unsupervised)
LBS Autoencoder: Self-supervised Fitting of Articulated Meshes to Point Clouds, CVPR 2019
[8]
BPS
Efficient Learning on Point Clouds with Basis Point Sets
[9]
Smooth Shells
Smooth Shells: Multi-Scale Shape Registration with Functional Maps, M Eisenberger, Z Lähner, D Cremers, CVPR, 2020
[10]
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
[11]
Unsupervised Cyclic mapper inter
Cyclic Functional Mapping: Self-supervised correspondence between non-isometric deformable shapes
[12]
JOMS-inter-female
Anonymous.
[13]
DHNN_ours2
Disentangled Human Body Embedding Based on Deep Hierarchical Neural Network. IEEE TVCG 2020
[14]
DHNN_ours1
Disentangled Human Body Embedding Based on Deep Hierarchical Neural Network. IEEE TVCG 2020
[15]
DHNN_ours_e1
Disentangled Human Body Embedding Based on Deep Hierarchical Neural Network. IEEE TVCG 2020
[16]
DHNN_ours_e2
Disentangled Human Body Embedding Based on Deep Hierarchical Neural Network. IEEE TVCG 2020
[17]
LSA-Conv: Learning localneighboring structure for robust 3d shape representation
Z. Gao, J. Yan, G. Zhai, J. Zhang, Y. Yang, and X. Yang, “Learning localneighboring structure for robust 3d shape representation,” inThirty-FifthAAAI Conference on Artificial Intelligence, 2021. TBD
[18]
Inter Test Fr
[19]
Inter Test FT2 LR Fr
Anonymous.
[20]
JOMS-inter-unisex
Anonymous.
[21]
JOMS-inter-male
Anonymous.
[22]
JOMS-inter-combined
Anonymous.
[23]
LoopReg
LoopReg: Self-supervised Learning of Implicit Surface Correspondences, Pose and Shape for 3D Human Mesh Registration, NeurIPS 2020 (oral)
[24]
Adversarial GP network
Reconstructing human body mesh from point clouds by adversarial GP network, ACCV2020
[25]
try_inter
Anonymous.
[26]
UD^2E-Net-Inter
Unsupervised Dense Deformation Embedding Network for Template-Free Shape Correspondence, ICCV2021
[27]
PAI_GCN
TBD TBD
[28]
Deep Virtual Marker (multi-view)
Deep Virtual Markers for Articulated 3D Shapes. ICCV 2021
[29]
Deep Virtual Marker (one-shot)
Deep Virtual Markers for Articulated 3D Shapes. ICCV 2021
[30]
PGMNet_Inter
Anonymous.
[31]
Anonymous
Anonymous.
[32]
Test-3D
Anonymous.
[33]
mp_inter_final
Anonymous.
[34]
h_inter_initial
Anonymous.
[35]
led_inter
Anonymous.
[36]
myaugreo
Anonymous.
[37]
Learning Shape Spaces via on-the-fly Correspondence Estimation
Anonymous. INTER