mlsanityData to 14 Oct 2026

SMPLer: Taming Transformers for Monocular 3D Human Shape and Pose Estimation

arXiv 2404.15276 ↗First posted 23 Apr 2024cs.CV cs.AI cs.GRcited by 9

Not on the map. Why?

Abstract (arXiv)

Existing Transformers for monocular 3D human shape and pose estimation typically have a quadratic computation and memory complexity with respect to the feature length, which hinders the exploitation of fine-grained information in high-resolution features that is beneficial for accurate reconstruction. In this work, we propose an SMPL-based Transformer framework (SMPLer) to address this issue. SMPLer incorporates two key ingredients: a decoupled attention operation and an SMPL-based target representation, which allow effective utilization of high-resolution features in the Transformer. In addition, based on these two designs, we also introduce several novel modules including a multi-scale attention and a joint-aware attention to further boost the reconstruction performance. Extensive experiments demonstrate the effectiveness of SMPLer against existing 3D human shape and pose estimation methods both quantitatively and qualitatively. Notably, the proposed algorithm achieves an MPJPE of 45.2 mm on the Human3.6M dataset, improving upon Mesh Graphormer by more than 10% with fewer than one-third of the parameters. Code and pretrained models are available at https://github.com/xuxy09/SMPLer.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 85 of its 109 references that are in the map. First posted on arXiv 23 Apr 2024.

Builds on

85 of 109 references.

References · 85

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  6. 2020End-to-End Object Detection with Transformerscited by 7,414
  7. 2016Layer Normalizationcited by 5,669
  8. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  9. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,612
  10. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  11. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,214
  12. 2017PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volumecited by 968
38 more
  1. 2020Pre-Trained Image Processing Transformercited by 893
  2. 2017End-to-end Recovery of Human Shape and Posecited by 885
  3. 2018Self-Attention Generative Adversarial Networkscited by 809
  4. 2016Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurringcited by 727
  5. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 695
  6. 2020Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humanscited by 634
  7. 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loopcited by 627
  8. 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 620
  9. 2021AI Choreographer: Music Conditioned 3D Dance Generation with AIST++cited by 485
  10. 2020End-to-End Human Pose and Mesh Reconstruction with Transformerscited by 418
  11. 2021PARE: Part Attention Regressor for 3D Human Body Estimationcited by 337
  12. 2018Learning 3D Human Dynamics from Videocited by 316
  13. 20163D Menagerie: Modeling the 3D shape and pose of animalscited by 312
  14. 2020HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimationcited by 307
  15. 2020I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Imagecited by 274
  16. 2019Convolutional Mesh Regression for Single-Image Human Shape Reconstructioncited by 270
  17. 2021Mesh Graphormercited by 265
  18. 2021PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loopcited by 250
  19. 2020Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Posecited by 248
  20. 2018Video Based Reconstruction of 3D People Modelscited by 238
  21. 2020PaMIR: Parametric Model-Conditioned Implicit Representation for Image-based Human Reconstructioncited by 231
  22. 2018Learning to Estimate 3D Human Pose and Shape from a Single Color Imagecited by 226
  23. 2020Monocular, One-stage, Regression of Multiple 3D Peoplecited by 218
  24. 2017Unite the People: Closing the Loop Between 3D and 2D Human Representationscited by 205
  25. 2017Single-Shot Multi-Person 3D Pose Estimation From Monocular RGBcited by 195
  26. 2018Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimationcited by 185
  27. 2021FrankMocap: A Monocular 3D Whole-Body Pose Estimation System via Regression and Integrationcited by 169
  28. 2019Learning to Reconstruct People in Clothing from a Single RGB Cameracited by 168
  29. 2019Tex2Shape: Detailed Full Human Body Geometry From a Single Imagecited by 166
  30. 2020Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Videocited by 163
  31. 2021TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Upcited by 162
  32. 2021Neural Human Performer: Learning Generalizable Radiance Fields for Human Performance Renderingcited by 158
  33. 2021Probabilistic Modeling for Human Mesh Recoverycited by 153
  34. 2021HRFormer: High-Resolution Transformer for Dense Predictioncited by 149
  35. 2020Coherent Reconstruction of Multiple Humans from a Single Imagecited by 136
  36. 2021SPEC: Seeing People in the Wild with an Estimated Cameracited by 135
  37. 2021Video Frame Interpolation Transformercited by 123
  38. 2020Exemplar Fine-Tuning for 3D Human Model Fitting Towards In-the-Wild 3D Human Pose Estimationcited by 113

50 most cited of 85 All 85 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 4; 2026: 3.

9 papers.

  1. 2024Generalizable Human Gaussians from Single-View Imagecited by 29
  2. 2024UniPose: A Unified Multimodal Framework for Human Pose Comprehension, Generation and Editingcited by 18
  3. 2026UniSH: Unifying Scene and Human Reconstruction in a Feed-Forward Passcited by 9
  4. 2025Geometric Neural Distance Fields for Learning Human Motion Priorscited by 6
  5. 2026UniMotion: A Unified Framework for Motion-Text-Vision Understanding and Generationcited by 4
  6. 2025EigenActor: Variant Body-Object Interaction Generation Evolved from Invariant Action Basis Reasoningcited by 1
  7. 2026UniCon3R: Unified Contact-aware 4D Human-Scene Reconstruction from Monocular Videocited by 1
  8. 2025PoseGRAF: Geometric-Reinforced Adaptive Fusion for Monocular 3D Human Pose Estimationcited by 0
  9. 2025Pose-RFT: Enhancing MLLMs for 3D Pose Generation via Hybrid Action Reinforcement Fine-Tuningcited by 0