mlsanityData to 7 Oct 2026

ShapeBoost: Boosting Human Shape Estimation with Part-Based Parameterization and Clothing-Preserving Augmentation

arXiv 2403.01345 ↗First posted 2 Mar 2024cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Accurate human shape recovery from a monocular RGB image is a challenging task because humans come in different shapes and sizes and wear different clothes. In this paper, we propose ShapeBoost, a new human shape recovery framework that achieves pixel-level alignment even for rare body shapes and high accuracy for people wearing different types of clothes. Unlike previous approaches that rely on the use of PCA-based shape coefficients, we adopt a new human shape parameterization that decomposes the human shape into bone lengths and the mean width of each part slice. This part-based parameterization technique achieves a balance between flexibility and validity using a semi-analytical shape reconstruction algorithm. Based on this new parameterization, a clothing-preserving data augmentation module is proposed to generate realistic images with diverse body shapes and accurate annotations. Experimental results show that our method outperforms other state-of-the-art methods in diverse body shape situations as well as in varied clothing situations.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 44 of its 51 references that are in the map. First posted on arXiv 2 Mar 2024.

Builds on

44 of 51 references.

References · 44

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,600
  3. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,417
  4. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,208
  5. 2017End-to-end Recovery of Human Shape and Posecited by 883
  6. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 692
  7. 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loopcited by 625
  8. 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 615
  9. 2020End-to-End Human Pose and Mesh Reconstruction with Transformerscited by 417
  10. 2017Learning from Synthetic Humanscited by 358
  11. 2021PARE: Part Attention Regressor for 3D Human Body Estimationcited by 334
  12. 2020HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimationcited by 304
32 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. 2019Convolutional Mesh Regression for Single-Image Human Shape Reconstructioncited by 270
  3. 2020Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Posecited by 248
  4. 2022CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimationcited by 237
  5. 2023BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motioncited by 229
  6. 2018Learning to Estimate 3D Human Pose and Shape from a Single Color Imagecited by 226
  7. 2021AGORA: Avatars in Geography Optimized for Regression Analysiscited by 203
  8. 2020STAR: Sparse Trained Articulated Human Body Regressorcited by 194
  9. 2018Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimationcited by 185
  10. 2020Monocular Expressive Body Regression through Body-Driven Attentioncited by 155
  11. 2022PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Imagescited by 152
  12. 2018BodyNet: Volumetric Inference of 3D Human Body Shapescited by 141
  13. 2020Exemplar Fine-Tuning for 3D Human Model Fitting Towards In-the-Wild 3D Human Pose Estimationcited by 113
  14. 2017Self-supervised Learning of Motion Capturecited by 97
  15. 2019InstaBoost: Boosting Instance Segmentation via Probability Map Guided Copy-Pastingcited by 95
  16. 2021On Self-Contact and Human Posecited by 88
  17. 2020Synthetic Training for Accurate 3D Human Pose and Shape Estimation in the Wildcited by 82
  18. 20193DPeople: Modeling the Geometry of Dressed Humanscited by 58
  19. 2022Accurate 3D Body Shape Regression using Metric and Semantic Attributescited by 49
  20. 2021Hierarchical Kinematic Probability Distributions for 3D Human Shape and Pose Estimation from Images in the Wildcited by 48
  21. 2023HybrIK-X: Hybrid Analytical-Neural Inverse Kinematics for Whole-body Mesh Recoverycited by 48
  22. 2023NIKI: Neural Inverse Kinematics with Invertible Neural Networks for 3D Human Pose and Shape Estimationcited by 45
  23. 20233D Human Mesh Estimation from Virtual Markerscited by 44
  24. 2021Probabilistic 3D Human Shape and Pose Estimation from Multiple Unconstrained Images in the Wildcited by 40
  25. 2021Learning to Regress Bodies from Images using Differentiable Semantic Renderingcited by 39
  26. 2022D&D: Learning Human Dynamics from Dynamic Cameracited by 39
  27. 2022Learned Vertex Descent: A New Direction for 3D Human Model Fittingcited by 37
  28. 2019Shape-Aware Human Pose and Shape Reconstruction Using Multi-View Imagescited by 28
  29. 2019Learning to Train with Synthetic Humanscited by 14
  30. 2021InfiniteForm: A synthetic, minimal bias dataset for fitness applicationscited by 5
  31. 2022Human Body Measurement Estimation with Adversarial Augmentationcited by 3
  32. 2023Shape of You: Precise 3D shape estimations for diverse body typescited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 1; 2026: 1.

4 papers.

  1. 2024Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimationcited by 57
  2. 2024ARTS: Semi-Analytical Regressor using Disentangled Skeletal Representations for Human Mesh Recovery from Videoscited by 4
  3. 2025ClothHMR: 3D Mesh Recovery of Humans in Diverse Clothing from Single Imagecited by 1
  4. 2026MoPO: Incorporating Motion Prior for Occluded Human Mesh Recoverycited by 0