Simple-baseline
|
A simple yet effective baseline for 3d human pose…
|
157.00
|
2017-05-08
|
|
HMR
|
End-to-end Recovery of Human Shape and Pose
|
130.00
|
2017-12-18
|
|
SMPLify
|
Keep it SMPL: Automatic Estimation of 3D Human Po…
|
106.80
|
2016-07-27
|
|
TP-Net
|
Learning 3D Human Pose from Structure and Motion
|
92.20
|
2017-11-25
|
|
MEEV
|
MEEV: Body Mesh Estimation On Egocentric Video
|
81.74
|
2022-10-21
|
|
MVM
|
Multi-View Matching (MVM): Facilitating Multi-Per…
|
78.20
|
2020-04-11
|
|
PARE + HANet (T=101)
|
Kinematic-aware Hierarchical Attention Network fo…
|
77.10
|
2022-11-29
|
|
PONet
|
PONet: Robust 3D Human Pose Estimation via Learni…
|
76.20
|
2021-12-21
|
|
ISO
|
Inference Stage Optimization for Cross-scenario 3…
|
75.80
|
2020-07-04
|
|
SMPLer-X
|
SMPLer-X: Scaling Up Expressive Human Pose and Sh…
|
75.20
|
2023-09-29
|
|
PARE + HANet (T=51)
|
Kinematic-aware Hierarchical Attention Network fo…
|
74.60
|
2022-11-29
|
|
HR-Net+ST-GCN+PoseAug
|
PoseAug: A Differentiable Pose Augmentation Frame…
|
73.20
|
2021-05-06
|
|
HMMR (T=20)
|
Learning 3D Human Dynamics from Video
|
72.60
|
2018-12-04
|
|
Non-Local Latent Relation Distillation
|
Non-Local Latent Relation Distillation for Self-A…
|
72.10
|
2022-04-05
|
|
HybridCap
|
HybridCap: Inertia-aid Monocular Capture of Chall…
|
72.10
|
2022-03-17
|
|
Spatio-Temporal Network (T=128)
|
3D Human Pose Estimation using Spatio-Temporal Ne…
|
71.80
|
2020-04-07
|
|
PoseTriplet
|
PoseTriplet: Co-evolving 3D Human Pose Estimation…
|
69.50
|
2022-03-29
|
|
PC-HMR
|
PC-HMR: Pose Calibration for 3D Human Mesh Recove…
|
66.90
|
2021-03-16
|
|
STRAPS
|
Synthetic Training for Accurate 3D Human Pose and…
|
66.80
|
2020-09-21
|
|
HW-HuP
|
Heuristic Weakly Supervised 3D Human Pose Estimat…
|
66.10
|
2021-05-23
|
|
UniHPE-w48
|
UniHPE: Towards Unified Human Pose Estimation via…
|
65.70
|
2023-11-24
|
|
ProHMR
|
Probabilistic Modeling for Human Mesh Recovery
|
65.00
|
2021-08-26
|
|
GnTCN
|
Graph and Temporal Convolutional Networks for 3D …
|
64.20
|
2020-12-22
|
|
BMP
|
Body Meshes as Points
|
63.80
|
2021-05-06
|
|
PoseNet3D
|
PoseNet3D: Learning Temporally Consistent 3D Huma…
|
63.20
|
2020-03-07
|
|
SHAPY (SMPL-X)
|
Accurate 3D Body Shape Regression using Metric an…
|
62.60
|
2022-06-14
|
|
Dual network
|
Dual networks based 3D Multi-Person Pose Estimati…
|
61.70
|
2022-05-02
|
|
Prob3DHumans
|
Probabilistic 3D Human Shape and Pose Estimation …
|
61.00
|
2021-03-19
|
|
ExPose
|
Monocular Expressive Body Regression through Body…
|
60.70
|
2020-08-20
|
|
MUG
|
MUG: Multi-human Graph Network for 3D Mesh Recons…
|
60.50
|
2022-05-25
|
|
FrankMocap
|
FrankMocap: A Monocular 3D Whole-Body Pose Estima…
|
60.00
|
2021-08-13
|
|
Biggs [3]
|
Probabilistic Modeling for Human Mesh Recovery
|
59.90
|
2021-08-26
|
|
THUNDR (WS)
|
THUNDR: Transformer-based 3D HUmaN Reconstruction…
|
59.90
|
2021-06-17
|
|
BeyondWeak
|
Beyond Weak Perspective for Monocular 3D Human Po…
|
59.70
|
2020-09-14
|
|
SPIN
|
Learning to Reconstruct 3D Human Pose and Shape v…
|
59.20
|
2019-09-27
|
|
RSC-Net
|
3D Human Shape and Pose from a Single Low-Resolut…
|
58.98
|
2020-07-27
|
|
GTRS
|
A Lightweight Graph Transformer Network for Human…
|
58.90
|
2021-11-24
|
|
LASOR
|
LASOR: Learning Accurate 3D Human Pose and Shape …
|
57.90
|
2021-08-01
|
|
HUND (FS+SS)
|
Neural Descent for Visual 3D Human Pose and Shape
|
57.50
|
2020-08-16
|
|
3DCrowdNet
|
Learning to Estimate Robust 3D Human Mesh from In…
|
55.80
|
2021-04-15
|
|
TCMR (T=16 w/o 3DPW)
|
Beyond Static Features for Temporally Consistent …
|
55.80
|
2020-11-17
|
|
TUCH
|
On Self-Contact and Human Pose
|
55.50
|
2021-04-07
|
|
ProHMR + fitting
|
Probabilistic Modeling for Human Mesh Recovery
|
55.10
|
2021-08-26
|
|
DaNet-DensePose2SMPL
|
Learning 3D Human Shape and Pose from Dense Body …
|
54.80
|
2019-12-31
|
|
Hand4Whole
|
Accurate 3D Hand Pose Estimation for Whole-Body 3…
|
54.40
|
2020-11-23
|
|
BlanketGen
|
BlanketGen - A synthetic blanket occlusion augmen…
|
53.96
|
2022-10-21
|
|
Hierarchical Probabilistic Humans
|
Hierarchical Kinematic Probability Distributions …
|
53.60
|
2021-10-03
|
|
HuManiFlow
|
HuManiFlow: Ancestor-Conditioned Normalising Flow…
|
53.40
|
2023-05-11
|
|
DDT
|
DiffMesh: A Motion-aware Diffusion Framework for …
|
53.30
|
2023-03-23
|
|
SPEC
|
SPEC: Seeing People in the Wild with an Estimated…
|
53.20
|
2021-10-01
|
|
MoCap-SPIN + PoseBERT
|
Leveraging MoCap Data for Human Mesh Recovery
|
52.90
|
2021-10-18
|
|
CLIFF
|
3D Human Reconstruction in the Wild with Syntheti…
|
52.70
|
2024-03-17
|
|
TCMR (T=16 w/o H3.6M)
|
Beyond Static Features for Temporally Consistent …
|
52.70
|
2020-11-17
|
|
STR
|
Spatio-temporal Tendency Reasoning for Human Body…
|
52.40
|
2022-10-07
|
|
MION
|
Multi-initialization Optimization Network for Acc…
|
52.34
|
2021-12-24
|
|
TePose (T=6)
|
Live Stream Temporally Embedded 3D Human Body Pos…
|
52.30
|
2022-07-25
|
|
MPS-Net (T=16)
|
Capturing Humans in Motion: Temporal-Attentive 3D…
|
52.10
|
2022-03-16
|
|
VIBE
|
VIBE: Video Inference for Human Body Pose and Sha…
|
51.90
|
2019-12-11
|
|
CHOMP
|
Occluded Human Body Capture with Self-Supervised …
|
51.70
|
2022-07-12
|
|
EFT
|
Exemplar Fine-Tuning for 3D Human Model Fitting T…
|
51.60
|
2020-04-07
|
|
UniHPE (GT)
|
UniHPE: Towards Unified Human Pose Estimation via…
|
51.60
|
2023-11-24
|
|
TAPE (T=16)
|
TAPE: Temporal Attention-based Probabilistic huma…
|
51.50
|
2023-04-29
|
|
THUNDR
|
THUNDR: Transformer-based 3D HUmaN Reconstruction…
|
51.50
|
2021-06-17
|
|
Wenshuo et a;.
|
Decomposed Human Motion Prior for Video Pose Esti…
|
51.40
|
2023-05-30
|
|
LMR
|
Learning Local Recurrent Models for Human Mesh Re…
|
51.20
|
2021-07-27
|
|
KAMA
|
KAMA: 3D Keypoint Aware Body Mesh Articulation
|
51.10
|
2021-04-27
|
|
CycleAdapt (w/o 2D GT)
|
Cyclic Test-Time Adaptation on Monocular Video fo…
|
51.10
|
2023-08-12
|
|
GLoT
|
Global-to-Local Modeling for Video-based 3D Human…
|
50.60
|
2023-03-26
|
|
Self-Attentive
|
Self-Attentive 3D Human Pose and Shape Estimation…
|
50.40
|
2021-03-26
|
|
DST-VIBE
|
Deep Two-Stream Video Inference for Human Body Po…
|
50.30
|
2021-10-22
|
|
FS+WS+OPT(KA+BA+S, 16 frames)
|
Weakly Supervised 3D Human Pose and Shape Reconst…
|
49.80
|
2020-03-23
|
|
MeTRAbs
|
MeTRAbs: Metric-Scale Truncation-Robust Heatmaps …
|
49.70
|
2020-07-12
|
|
BOA (w/ 2D GT)
|
Bilevel Online Adaptation for Out-of-Domain Human…
|
49.50
|
2021-03-30
|
|
TCFormer
|
Not All Tokens Are Equal: Human-centric Visual An…
|
49.30
|
2022-04-19
|
|
MotionBERT (Finetune)
|
MotionBERT: A Unified Perspective on Learning Hum…
|
47.20
|
2022-10-12
|
|
ARTS (Resnet50 L=16)
|
ARTS: Semi-Analytical Regressor using Disentangle…
|
46.50
|
2024-10-21
|
|
DeciWatch-PARE
|
DeciWatch: A Simple Baseline for 10x Efficient 2D…
|
46.40
|
2022-03-16
|
|
IVT (f=5)
|
IVT: An End-to-End Instance-guided Video Transfor…
|
46.00
|
2022-08-06
|
|
HeatER
|
FeatER: An Efficient Network for Human Reconstruc…
|
45.90
|
2022-05-30
|
|
XFormer (HRNet)
|
XFormer: Fast and Accurate Monocular 3D Body Capt…
|
45.70
|
2023-05-18
|
|
ImpHMR
|
Implicit 3D Human Mesh Recovery using Consistency…
|
45.40
|
2023-06-30
|
|
OSX
|
One-Stage 3D Whole-Body Mesh Recovery with Compon…
|
45.10
|
2023-03-28
|
|
HybrIK
|
HybrIK: A Hybrid Analytical-Neural Inverse Kinema…
|
45.00
|
2020-11-30
|
|
POTTER
|
POTTER: Pooling Attention Transformer for Efficie…
|
44.80
|
2023-03-23
|
|
IKOL
|
IKOL: Inverse kinematics optimization layer for 3…
|
44.50
|
2023-02-02
|
|
HMR 2.0
|
Humans in 4D: Reconstructing and Tracking Humans …
|
44.40
|
2023-05-31
|
|
TokenHMR (SD + ITW + BL)
|
TokenHMR: Advancing Human Mesh Recovery with a To…
|
44.30
|
2024-04-25
|
|
RemoCap
|
RemoCap: Disentangled Representation Learning for…
|
44.10
|
2024-05-21
|
|
PSVT
|
PSVT: End-to-End Multi-person 3D Pose and Shape E…
|
43.50
|
2023-03-16
|
|
SMPLer-L
|
SMPLer: Taming Transformers for Monocular 3D Huma…
|
43.40
|
2024-04-23
|
|
MPT
|
MPT: Mesh Pre-Training with Transformers for Huma…
|
42.80
|
2022-11-24
|
|
ZeDO (Cross Dataset)
|
Back to Optimization: Diffusion-based Zero-Shot 3…
|
42.60
|
2023-07-07
|
|
BoPR (HR-W48)
|
BoPR: Body-aware Part Regressor for Human Shape a…
|
42.50
|
2023-03-21
|
|
HybrIK-Transformer (HrNet-48)
|
3D Human Pose and Shape Estimation via HybrIK-Tra…
|
42.30
|
2023-02-09
|
|
3DHR-Co (w/ 2D GT)
|
3DHR-Co: A Collaborative Test-time Refinement Fra…
|
42.11
|
2023-10-02
|
|
GenHMR
|
GenHMR: Generative Human Mesh Recovery
|
42.10
|
2024-12-19
|
|
PROM (CLIFF)
|
Learning Unorthogonalized Matrices for Rotation E…
|
42.00
|
2023-12-01
|
|
INT-2 (ResNet-50)
|
Capturing the motion of every joint: 3D human pos…
|
42.00
|
2023-03-01
|
|
CLIFF (3DPW+HumanWild+BEDLAM+AGORA)
|
3D Human Reconstruction in the Wild with Syntheti…
|
41.90
|
2024-03-17
|
|
HybrIK (HRNet-W48)
|
HybrIK-X: Hybrid Analytical-Neural Inverse Kinema…
|
41.80
|
2023-04-12
|
|
VirtualMarker
|
3D Human Mesh Estimation from Virtual Markers
|
41.30
|
2023-03-21
|
|
PostoMETRO (ResNet-50)
|
PostoMETRO: Pose Token Enhanced Mesh Transformer …
|
40.80
|
2024-03-19
|
|
MotionBERT-HybrIK
|
MotionBERT: A Unified Perspective on Learning Hum…
|
40.60
|
2022-10-12
|
|
TAR (N=9)
|
Temporal-Aware Refinement for Video-based Human P…
|
40.60
|
2023-11-16
|
|
NIKI (Twist-and-Swing)
|
NIKI: Neural Inverse Kinematics with Invertible N…
|
40.60
|
2023-05-15
|
|
DynaBOA (w/ 2D GT)
|
Out-of-Domain Human Mesh Reconstruction via Dynam…
|
40.40
|
2021-11-07
|
|
ZeDO (S=1,J=17)
|
Back to Optimization: Diffusion-based Zero-Shot 3…
|
40.30
|
2023-07-07
|
|
CycleAdapt (w/ 2D GT)
|
Cyclic Test-Time Adaptation on Monocular Video fo…
|
39.90
|
2023-08-12
|
|
Hulk(ViT-B)
|
Hulk: A Universal Knowledge Translator for Human-…
|
39.90
|
2023-12-04
|
|
Zolly (HRNet-w48)
|
Zolly: Zoom Focal Length Correctly for Perspectiv…
|
39.80
|
2023-03-24
|
|
PostoMETRO (HRNet-w48)
|
PostoMETRO: Pose Token Enhanced Mesh Transformer …
|
39.80
|
2024-03-19
|
|
BioPose
|
BioPose: Biomechanically-accurate 3D Pose Estimat…
|
39.50
|
2025-01-14
|
|
Hulk(ViT-L)
|
Hulk: A Universal Knowledge Translator for Human-…
|
38.50
|
2023-12-04
|
|
TRACE
|
TRACE: 5D Temporal Regression of Avatars with Dyn…
|
37.80
|
2023-06-05
|
|
WHAM (ViT)
|
WHAM: Reconstructing World-grounded Humans with A…
|
35.90
|
2023-12-12
|
|