| 1 | HMR | 130 | No | End-to-end Recovery of Human Shape and Pose | 2017-12-18 | Code |
| 2 | HMMR (T=20) | 116.5 | No | Learning 3D Human Dynamics from Video | 2018-12-04 | Code |
| 3 | PoseTriplet | 115 | No | PoseTriplet: Co-evolving 3D Human Pose Estimatio... | 2022-03-29 | Code |
| 4 | BMP | 104.1 | No | Body Meshes as Points | 2021-05-06 | Code |
| 5 | SPIN | 96.9 | No | Learning to Reconstruct 3D Human Pose and Shape ... | 2019-09-27 | Code |
| 6 | RSC-Net | 96.36 | No | 3D Human Shape and Pose from a Single Low-Resolu... | 2020-07-27 | Code |
| 7 | SHAPY (SMPL-X) | 95.2 | No | Accurate 3D Body Shape Regression using Metric a... | 2022-06-14 | Code |
| 8 | TCMR (T=16 w/o 3DPW) | 95 | No | Beyond Static Features for Temporally Consistent... | 2020-11-17 | Code |
| 9 | FrankMocap | 94.3 | No | FrankMocap: A Monocular 3D Whole-Body Pose Estim... | 2021-08-13 | Code |
| 10 | ExPose | 93.4 | No | Monocular Expressive Body Regression through Bod... | 2020-08-20 | Code |
| 11 | Prob3DHumans | 90.9 | No | Probabilistic 3D Human Shape and Pose Estimation... | 2021-03-19 | - |
| 12 | MoCap-SPIN + PoseBERT | 89.4 | No | Leveraging MoCap Data for Human Mesh Recovery | 2021-10-18 | Code |
| 13 | Wenshuo et a;. | 89.4 | No | Decomposed Human Motion Prior for Video Pose Est... | 2023-05-30 | - |
| 14 | GTRS | 88.5 | No | A Lightweight Graph Transformer Network for Huma... | 2021-11-24 | Code |
| 15 | PC-HMR | 87.8 | No | PC-HMR: Pose Calibration for 3D Human Mesh Recov... | 2021-03-16 | - |
| 16 | CLIFF | 87.3 | No | 3D Human Reconstruction in the Wild with Synthet... | 2024-03-17 | - |
| 17 | MUG | 87 | No | MUG: Multi-human Graph Network for 3D Mesh Recon... | 2022-05-25 | - |
| 18 | THUNDR (WS) | 86.8 | No | THUNDR: Transformer-based 3D HUmaN Reconstructio... | 2021-06-17 | - |
| 19 | TCMR (T=16 w/o H3.6M) | 86.5 | No | Beyond Static Features for Temporally Consistent... | 2020-11-17 | Code |
| 20 | DDT | 85.9 | No | DiffMesh: A Motion-aware Diffusion Framework for... | 2023-03-23 | - |
| 21 | Self-Attentive | 85.8 | No | Self-Attentive 3D Human Pose and Shape Estimatio... | 2021-03-26 | - |
| 22 | 3DCrowdNet | 85.8 | No | Learning to Estimate Robust 3D Human Mesh from I... | 2021-04-15 | Code |
| 23 | DaNet-DensePose2SMPL | 85.5 | No | Learning 3D Human Shape and Pose from Dense Body... | 2019-12-31 | Code |
| 24 | STR | 85.2 | No | Spatio-temporal Tendency Reasoning for Human Bod... | 2022-10-07 | - |
| 25 | Hierarchical Probabilistic Humans | 84.9 | No | Hierarchical Kinematic Probability Distributions... | 2021-10-03 | Code |
| 26 | TUCH | 84.9 | No | On Self-Contact and Human Pose | 2021-04-07 | Code |
| 27 | TePose (T=6) | 84.6 | No | Live Stream Temporally Embedded 3D Human Body Po... | 2022-07-25 | Code |
| 28 | CycleAdapt (w/o 2D GT) | 84.4 | No | Cyclic Test-Time Adaptation on Monocular Video f... | 2023-08-12 | Code |
| 29 | MPS-Net (T=16) | 84.3 | No | Capturing Humans in Motion: Temporal-Attentive 3... | 2022-03-16 | - |
| 30 | HuManiFlow | 83.9 | No | HuManiFlow: Ancestor-Conditioned Normalising Flo... | 2023-05-11 | Code |
| 31 | CHOMP | 83.7 | No | Occluded Human Body Capture with Self-Supervised... | 2022-07-12 | Code |
| 32 | BeyondWeak | 83.2 | No | Beyond Weak Perspective for Monocular 3D Human P... | 2020-09-14 | - |
| 33 | VIBE | 82.9 | No | VIBE: Video Inference for Human Body Pose and Sh... | 2019-12-11 | Code |
| 34 | MION | 81.98 | No | Multi-initialization Optimization Network for Ac... | 2021-12-24 | - |
| 35 | MEEV | 81.74 | No | MEEV: Body Mesh Estimation On Egocentric Video | 2022-10-21 | Code |
| 36 | LMR | 81.7 | No | Learning Local Recurrent Models for Human Mesh R... | 2021-07-27 | - |
| 37 | HUND (FS+SS) | 81.4 | No | Neural Descent for Visual 3D Human Pose and Shape | 2020-08-16 | - |
| 38 | ZeDO (Cross Dataset) | 80.9 | No | Back to Optimization: Diffusion-based Zero-Shot ... | 2023-07-07 | Code |
| 39 | GLoT | 80.7 | No | Global-to-Local Modeling for Video-based 3D Huma... | 2023-03-26 | Code |
| 40 | TCFormer | 80.6 | No | Not All Tokens Are Equal: Human-centric Visual A... | 2022-04-19 | Code |
| 41 | FS+WS+OPT(KA+BA+S, 16 frames) | 80.2 | No | Weakly Supervised 3D Human Pose and Shape Recons... | 2020-03-23 | - |
| 42 | TAPE (T=16) | 79.9 | No | TAPE: Temporal Attention-based Probabilistic hum... | 2023-04-29 | Code |
| 43 | TRACE | 79.1 | No | TRACE: 5D Temporal Regression of Avatars with Dy... | 2023-06-05 | Code |
| 44 | SEFD | 77.37 | No | - | - | Code |
| 45 | BOA (w/ 2D GT) | 77.2 | No | Bilevel Online Adaptation for Out-of-Domain Huma... | 2021-03-30 | Code |
| 46 | PARE + HANet (T=101) | 77.1 | No | Kinematic-aware Hierarchical Attention Network f... | 2022-11-29 | Code |
| 47 | MotionBERT (Finetune) | 76.9 | No | MotionBERT: A Unified Perspective on Learning Hu... | 2022-10-12 | Code |
| 48 | DST-VIBE | 76.7 | No | Deep Two-Stream Video Inference for Human Body P... | 2021-10-22 | - |
| 49 | INT-2 (ResNet-50) | 75.6 | No | Capturing the motion of every joint: 3D human po... | 2023-03-01 | Code |
| 50 | DeciWatch-PARE | 75.5 | No | DeciWatch: A Simple Baseline for 10x Efficient 2... | 2022-03-16 | Code |
| 51 | SMPLer-X | 75.2 | No | SMPLer-X: Scaling Up Expressive Human Pose and S... | 2023-09-29 | Code |
| 52 | XFormer (HRNet) | 75 | No | XFormer: Fast and Accurate Monocular 3D Body Cap... | 2023-05-18 | - |
| 53 | POTTER | 75 | No | POTTER: Pooling Attention Transformer for Effici... | 2023-03-23 | Code |
| 54 | THUNDR | 74.8 | No | THUNDR: Transformer-based 3D HUmaN Reconstructio... | 2021-06-17 | - |
| 55 | OSX | 74.7 | No | One-Stage 3D Whole-Body Mesh Recovery with Compo... | 2023-03-28 | Code |
| 56 | PARE + HANet (T=51) | 74.6 | No | Kinematic-aware Hierarchical Attention Network f... | 2022-11-29 | Code |
| 57 | ImpHMR | 74.3 | No | Implicit 3D Human Mesh Recovery using Consistenc... | 2023-06-30 | - |
| 58 | HybrIK | 74.1 | No | HybrIK: A Hybrid Analytical-Neural Inverse Kinem... | 2020-11-30 | Code |
| 59 | SMPLer-L | 73.7 | No | SMPLer: Taming Transformers for Monocular 3D Hum... | 2024-04-23 | Code |
| 60 | HeatER | 73.4 | No | FeatER: An Efficient Network for Human Reconstru... | 2022-05-30 | Code |
| 61 | PSVT | 73.1 | No | PSVT: End-to-End Multi-person 3D Pose and Shape ... | 2023-03-16 | - |
| 62 | DeFormer | 72.9 | No | - | - | Code |
| 63 | RemoCap | 72.7 | No | RemoCap: Disentangled Representation Learning fo... | 2024-05-21 | - |
| 64 | HybridCap | 72.1 | No | HybridCap: Inertia-aid Monocular Capture of Chal... | 2022-03-17 | - |
| 65 | HybrIK (HRNet-W48) | 71.6 | No | HybrIK-X: Hybrid Analytical-Neural Inverse Kinem... | 2023-04-12 | Code |
| 66 | HybrIK-Transformer (HrNet-48) | 71.6 | No | 3D Human Pose and Shape Estimation via HybrIK-Tr... | 2023-02-09 | Code |
| 67 | NIKI (Twist-and-Swing) | 71.3 | No | NIKI: Neural Inverse Kinematics with Invertible ... | 2023-05-15 | Code |
| 68 | IKOL | 71.1 | No | IKOL: Inverse kinematics optimization layer for ... | 2023-02-02 | Code |
| 69 | TokenHMR (SD + ITW + BL) | 71 | No | TokenHMR: Advancing Human Mesh Recovery with a T... | 2024-04-25 | Code |
| 70 | HMR 2.0 | 69.8 | No | Humans in 4D: Reconstructing and Tracking Humans... | 2023-05-31 | Code |
| 71 | ZeDO (S=1,J=17) | 69.7 | No | Back to Optimization: Diffusion-based Zero-Shot ... | 2023-07-07 | Code |
| 72 | BioPose | 69 | No | BioPose: Biomechanically-accurate 3D Pose Estima... | 2025-01-14 | - |
| 73 | MotionBERT-HybrIK | 68.8 | No | MotionBERT: A Unified Perspective on Learning Hu... | 2022-10-12 | Code |
| 74 | MeTRAbs | 68.8 | No | MeTRAbs: Metric-Scale Truncation-Robust Heatmaps... | 2020-07-12 | Code |
| 75 | PostoMETRO (ResNet-50) | 68.4 | No | PostoMETRO: Pose Token Enhanced Mesh Transformer... | 2024-03-19 | - |
| 76 | GenHMR | 68.1 | No | GenHMR: Generative Human Mesh Recovery | 2024-12-19 | - |
| 77 | PostoMETRO (HRNet-w48) | 67.7 | No | PostoMETRO: Pose Token Enhanced Mesh Transformer... | 2024-03-19 | - |
| 78 | ARTS (Resnet50 L=16) | 67.7 | No | ARTS: Semi-Analytical Regressor using Disentangl... | 2024-10-21 | Code |
| 79 | PROM (CLIFF) | 67.6 | No | Learning Unorthogonalized Matrices for Rotation ... | 2023-12-01 | - |
| 80 | VirtualMarker | 67.5 | No | 3D Human Mesh Estimation from Virtual Markers | 2023-03-21 | Code |
| 81 | Hulk(ViT-B) | 67 | No | Hulk: A Universal Knowledge Translator for Human... | 2023-12-04 | Code |
| 82 | Hulk(ViT-L) | 66.3 | No | Hulk: A Universal Knowledge Translator for Human... | 2023-12-04 | Code |
| 83 | MPT | 65.9 | No | MPT: Mesh Pre-Training with Transformers for Hum... | 2022-11-24 | Code |
| 84 | DynaBOA (w/ 2D GT) | 65.5 | No | Out-of-Domain Human Mesh Reconstruction via Dyna... | 2021-11-07 | Code |
| 85 | BoPR (HR-W48) | 65.4 | No | BoPR: Body-aware Part Regressor for Human Shape ... | 2023-03-21 | Code |
| 86 | CLIFF (3DPW+HumanWild+BEDLAM+AGORA) | 65.2 | No | 3D Human Reconstruction in the Wild with Synthet... | 2024-03-17 | - |
| 87 | Zolly (HRNet-w48) | 65 | No | Zolly: Zoom Focal Length Correctly for Perspecti... | 2023-03-24 | Code |
| 88 | SEFD_GT | 64.75 | No | - | - | Code |
| 89 | CycleAdapt (w/ 2D GT) | 64.7 | No | Cyclic Test-Time Adaptation on Monocular Video f... | 2023-08-12 | Code |
| 90 | 3DHR-Co (w/ 2D GT) | 63.72 | No | 3DHR-Co: A Collaborative Test-time Refinement Fr... | 2023-10-02 | - |
| 91 | TAR (N=9) | 62.7 | No | Temporal-Aware Refinement for Video-based Human ... | 2023-11-16 | - |
| 92 | WHAM (ViT) | 57.8 | No | WHAM: Reconstructing World-grounded Humans with ... | 2023-12-12 | Code |
| 93 | ExtPose (-a, T=16) | 54.2 | No | - | - | - |