mlsanityData to 7 Oct 2026

D3L: Decomposition of 3D Rotation and Lift from 2D Joint to 3D for Human Mesh Recovery

arXiv 2306.06406 ↗First posted 10 Jun 2023cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Existing methods for 3D human mesh recovery always directly estimate SMPL parameters, which involve both joint rotations and shape parameters. However, these methods present rotation semantic ambiguity, rotation error accumulation, and shape estimation overfitting, which also leads to errors in the estimated pose. Additionally, these methods have not efficiently leveraged the advancements in another hot topic, human pose estimation. To address these issues, we propose a novel approach, Decomposition of 3D Rotation and Lift from 2D Joint to 3D mesh (D3L). We disentangle 3D joint rotation into bone direction and bone twist direction so that the human mesh recovery task is broken down into estimation of pose, twist, and shape, which can be handled independently. Then we design a 2D-to-3D lifting network for estimating twist direction and 3D joint position from 2D joint position sequences and introduce a nonlinear optimization method for fitting shape parameters and bone directions. Our approach can leverage human pose estimation methods, and avoid pose errors introduced by shape estimation overfitting. We conduct experiments on the Human3.6M dataset and demonstrate improved performance compared to existing methods by a large margin.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 22 of its 33 references that are in the map. First posted on arXiv 10 Jun 2023.

Builds on

22 of 33 references.

References · 22

  1. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,600
  2. 2017End-to-end Recovery of Human Shape and Posecited by 883
  3. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 692
  4. 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loopcited by 625
  5. 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 615
  6. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  7. 2021PARE: Part Attention Regressor for 3D Human Body Estimationcited by 334
  8. 2018Learning 3D Human Dynamics from Videocited by 315
  9. 2020HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimationcited by 304
  10. 2020I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Imagecited by 274
  11. 2019Convolutional Mesh Regression for Single-Image Human Shape Reconstructioncited by 270
  12. 2021PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loopcited by 250
10 more
  1. 2020Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Posecited by 248
  2. 2018Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodiescited by 239
  3. 2018Learning to Estimate 3D Human Pose and Shape from a Single Color Imagecited by 226
  4. 2018Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimationcited by 185
  5. 2020Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Videocited by 162
  6. 2022MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Videocited by 158
  7. 2019Human Mesh Recovery from Monocular Images via a Skeleton-disentangled Representationcited by 87
  8. 2020Hierarchical Kinematic Human Mesh Recoverycited by 71
  9. 20203D Human Mesh Regression with Dense Correspondencecited by 66
  10. 2020NeuralAnnot: Neural Annotator for 3D Human Mesh Training Setscited by 62

Built on by

Not cited yet.