mlsanityData to 14 Oct 2026

VolNet: Estimating Human Body Part Volumes from a Single RGB Image

arXiv 2107.02259 ↗First posted 5 Jul 2021cs.CV cs.AI cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

Human body volume estimation from a single RGB image is a challenging problem despite minimal attention from the research community. However VolNet, an architecture leveraging 2D and 3D pose estimation, body part segmentation and volume regression extracted from a single 2D RGB image combined with the subject's body height can be used to estimate the total body volume. VolNet is designed to predict the 2D and 3D pose as well as the body part segmentation in intermediate tasks. We generated a synthetic, large-scale dataset of photo-realistic images of human bodies with a wide range of body shapes and realistic poses called SURREALvols. By using Volnet and combining multiple stacked hourglass networks together with ResNeXt, our model correctly predicted the volume in ~82% of cases with a 10% tolerance threshold. This is a considerable improvement compared to state-of-the-art solutions such as BodyNet with only a ~38% success rate.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 22 of its 45 references that are in the map. First posted on arXiv 5 Jul 2021.

Builds on

22 of 45 references.

References · 22

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  3. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,546
  4. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,355
  5. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 915
  6. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 695
  7. 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loopcited by 627
  8. 2013Domain Generalization via Invariant Feature Representationcited by 623
  9. 2018DensePose: Dense Human Pose Estimation In The Wildcited by 575
  10. 2017Learning from Synthetic Humanscited by 359
  11. 2013DeepPose: Human Pose Estimation via Deep Neural Networkscited by 305
  12. 2018Learning to Estimate 3D Human Pose and Shape from a Single Color Imagecited by 226
10 more
  1. 2019BSP-Net: Generating Compact Meshes via Binary Space Partitioningcited by 206
  2. 2017Unite the People: Closing the Loop Between 3D and 2D Human Representationscited by 205
  3. 2019Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wildcited by 180
  4. 2019Tex2Shape: Detailed Full Human Body Geometry From a Single Imagecited by 166
  5. 2020DeepCap: Monocular Human Performance Capture Using Weak Supervisioncited by 162
  6. 2018BodyNet: Volumetric Inference of 3D Human Body Shapescited by 141
  7. 2018Detailed Human Avatars from Monocular Videocited by 109
  8. 2019DenseRaC: Joint 3D Pose and Shape Estimation by Dense Render-and-Comparecited by 100
  9. 2017Detailed, accurate, human shape estimation from clothed 3D scan sequencescited by 89
  10. 2019Moulding Humans: Non-parametric 3D Human Shape Estimation from Single Imagescited by 67

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Lightweight Neural Framework for Robust 3D Volume and Surface Estimation from Multi-View Imagescited by 0