mlsanityData to 7 Oct 2026

3D Human Pose Lifting with Grid Convolution

arXiv 2302.08760 ↗First posted 17 Feb 2023cs.CV cs.AI cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

Existing lifting networks for regressing 3D human poses from 2D single-view poses are typically constructed with linear layers based on graph-structured representation learning. In sharp contrast to them, this paper presents Grid Convolution (GridConv), mimicking the wisdom of regular convolution operations in image space. GridConv is based on a novel Semantic Grid Transformation (SGT) which leverages a binary assignment matrix to map the irregular graph-structured human pose onto a regular weave-like grid pose representation joint by joint, enabling layer-wise feature learning with GridConv operations. We provide two ways to implement SGT, including handcrafted and learnable designs. Surprisingly, both designs turn out to achieve promising results and the learnable one is better, demonstrating the great potential of this new lifting representation learning formulation. To improve the ability of GridConv to encode contextual cues, we introduce an attention module over the convolutional kernel, making grid convolution operations input-dependent, spatial-aware and grid-specific. We show that our fully convolutional grid lifting network outperforms state-of-the-art methods with noticeable margins under (1) conventional evaluation on Human3.6M and (2) cross-evaluation on MPI-INF-3DHP. Code is available at https://github.com/OSVAI/GridConv

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 36 of its 52 references that are in the map. First posted on arXiv 17 Feb 2023.

Builds on

36 of 52 references.

References · 36

  1. 2017Squeeze-and-Excitation Networkscited by 4,763
  2. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  3. 2018CBAM: Convolutional Block Attention Modulecited by 2,463
  4. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  5. 2018OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,161
  6. 2017End-to-end Recovery of Human Shape and Posecited by 883
  7. 2015BinaryConnect: Training Deep Neural Networks with binary weights during propagationscited by 571
  8. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 493
  9. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  10. 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 401
  11. 2019Dynamic Convolution: Attention over Convolution Kernelscited by 355
  12. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
24 more
  1. 2020I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Imagecited by 274
  2. 2019CondConv: Conditionally Parameterized Convolutions for Efficient Inferencecited by 273
  3. 2017Integral Human Pose Regressioncited by 255
  4. 2016Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Posecited by 220
  5. 2019Semantic Graph Convolutional Networks for 3D Human Pose Regressioncited by 204
  6. 2017Single-Shot Multi-Person 3D Pose Estimation From Monocular RGBcited by 195
  7. 2019Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Imagecited by 131
  8. 2017VNect: Real-time 3D Human Pose Estimation with a Single RGB Cameracited by 129
  9. 2017Compositional Human Pose Regressioncited by 124
  10. 2017Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approachcited by 114
  11. 2020SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approachcited by 94
  12. 2019Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Networkcited by 92
  13. 2021PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimationcited by 88
  14. 20183D Human Pose Estimation in the Wild by Adversarial Learningcited by 86
  15. 2020Cascaded deep monocular 3D human pose estimation with evolutionary training datacited by 80
  16. 2019Monocular 3D Human Pose Estimation by Generation and Ordinal Rankingcited by 76
  17. 2021Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimationcited by 62
  18. 2015Sparseness Meets Deepness: 3D Human Pose Estimation from Monocular Videocited by 54
  19. 2021Conditional Directed Graph Convolution for 3D Human Pose Estimationcited by 52
  20. 2020WeightNet: Revisiting the Design Space of Weight Networkscited by 50
  21. 2018OriNet: A Fully Convolutional Network for 3D Human Pose Estimationcited by 28
  22. 2019Context-Gated Convolutioncited by 23
  23. 2020PCLs: Geometry-aware Neural Reconstruction of 3D Pose with Perspective Crop Layerscited by 16
  24. 2020HEMlets PoSh: Learning Part-Centric Heatmap Triplets for 3D Human Pose and Shape Estimationcited by 12

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 1.

2 papers.

  1. 2023Ske2Grid: Skeleton-to-Grid Representation Learning for Action Recognitioncited by 7
  2. 2024Pre-training a Density-Aware Pose Transformer for Robust LiDAR-based 3D Human Pose Estimationcited by 4