mlsanityData to 14 Oct 2026

Error Estimation for Single-Image Human Body Mesh Reconstruction

arXiv 2305.17245 ↗First posted 26 May 2023cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Human pose and shape estimation methods continue to suffer in situations where one or more parts of the body are occluded. More importantly, these methods cannot express when their predicted pose is incorrect. This has serious consequences when these methods are used in human-robot interaction scenarios, where we need methods that can evaluate their predictions and flag situations where they might be wrong. This work studies this problem. We propose a method that combines information from OpenPose and SPIN -- two popular human pose and shape estimation methods -- to highlight regions on the predicted mesh that are least reliable. We have evaluated the proposed approach on 3DPW, 3DOH, and Human3.6M datasets, and the results demonstrate our model's effectiveness in identifying inaccurate regions of the human body mesh. Our code is available at https://github.com/Hamoon1987/meshConfidence.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 26 of its 32 references that are in the map. First posted on arXiv 26 May 2023.

Builds on

26 of 32 references.

References · 26

  1. 2013Visualizing and Understanding Convolutional Networkscited by 2,290
  2. 2017Random Erasing Data Augmentationcited by 1,239
  3. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,064
  4. 2017End-to-end Recovery of Human Shape and Posecited by 885
  5. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 695
  6. 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loopcited by 627
  7. 2021PARE: Part Attention Regressor for 3D Human Body Estimationcited by 337
  8. 2020HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimationcited by 307
  9. 2018Learning to Estimate 3D Human Pose and Shape from a Single Color Imagecited by 226
  10. 2017Unite the People: Closing the Loop Between 3D and 2D Human Representationscited by 205
  11. 2018Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimationcited by 185
  12. 2019Distribution-Aware Coordinate Representation for Human Pose Estimationcited by 165
14 more
  1. 2017Compositional Human Pose Regressioncited by 124
  2. 2015DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimationcited by 117
  3. 2018Modeling Visual Context is Key to Augmenting Object Detection Datasetscited by 106
  4. 2022Recovering 3D Human Mesh from Monocular Images: A Surveycited by 103
  5. 2017Self-supervised Learning of Motion Capturecited by 97
  6. 2016DeeperCut: A Deeper, Stronger, and Faster Multi-Person Pose Estimation Modelcited by 96
  7. 2020Hierarchical Kinematic Human Mesh Recoverycited by 71
  8. 2022Occluded Human Mesh Recoverycited by 54
  9. 2017Human Pose Regression by Combining Indirect Part Detection and Contextual Informationcited by 52
  10. 2018Multi-Scale Structure-Aware Network for Human Pose Estimationcited by 37
  11. 2017Adversarial PoseNet: A Structure-aware Convolutional Network for Human Pose Estimationcited by 35
  12. 2018How Robust is 3D Human Pose Estimation to Occlusion?cited by 23
  13. 2017Human Pose Estimation using Global and Local Normalizationcited by 10
  14. 2019Real-time Convolutional Networks for Depth-based Human Pose Estimationcited by 4

Built on by

Not cited yet.