Human Body Measurement Estimation with Adversarial Augmentation

• URL: http://arxiv.org/abs/2210.05667v1
• Date: Tue, 11 Oct 2022 17:58:10 GMT
• Title: Human Body Measurement Estimation with Adversarial Augmentation
• Authors: Nataniel Ruiz, Miriam Bellver, Timo Bolkart, Ambuj Arora, Ming C. Lin, Javier Romero, Raja Bala
• Abstract summary: We present a Body Measurement network (BMnet) for estimating 3D anthropomorphic measurements of the human body shape from silhouette images. We augmented BMnet with a novel adversarial body simulator (ABS) that finds and synthesizes challenging body shapes. Results show that training BMnet with ABS improves measurement prediction accuracy on real bodies by up to 10%, when compared to no augmentation or random body shape sampling.
• Score: 28.934387668050224
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present a Body Measurement network (BMnet) for estimating 3D anthropomorphic measurements of the human body shape from silhouette images. Training of BMnet is performed on data from real human subjects, and augmented with a novel adversarial body simulator (ABS) that finds and synthesizes challenging body shapes. ABS is based on the skinned multiperson linear (SMPL) body model, and aims to maximize BMnet measurement prediction error with respect to latent SMPL shape parameters. ABS is fully differentiable with respect to these parameters, and trained end-to-end via backpropagation with BMnet in the loop. Experiments show that ABS effectively discovers adversarial examples, such as bodies with extreme body mass indices (BMI), consistent with the rarity of extreme-BMI bodies in BMnet's training set. Thus ABS is able to reveal gaps in training data and potential failures in predicting under-represented body shapes. Results show that training BMnet with ABS improves measurement prediction accuracy on real bodies by up to 10%, when compared to no augmentation or random body shape sampling. Furthermore, our method significantly outperforms SOTA measurement estimation methods by as much as 3x. Finally, we release BodyM, the first challenging, large-scale dataset of photo silhouettes and body measurements of real human subjects, to further promote research in this area. Project website: https://adversarialbodysim.github.io

Related papers

• Leveraging Anthropometric Measurements to Improve Human Mesh Estimation and Ensure Consistent Body Shapes [12.932412290302258]
  A2B is a model that converts anthropometric measurements to body shape parameters of human mesh models. We show that finetuned SOTA 3D human pose estimation (HPE) models outperform HME models regarding the precision of the estimated keypoints. We also show that replacing HME models estimates of the body shape parameters with A2B model results not only increases the performance of these HME models, but also leads to consistent body shapes.
  arXiv  Detail & Related papers  (2024-09-26T09:30:37Z)
• BMI Prediction from Handwritten English Characters Using a Convolutional Neural Network [0.0]
  No previous research established a clear connection between deep learning techniques for handwriting analysis and BMI prediction. This article addresses this research gap with a deep learning approach to estimating BMI from handwritten characters by developing a convolutional neural network (CNN) A dataset containing samples from 48 people in lowercase English scripts is successfully captured for the BMI prediction task.
  arXiv  Detail & Related papers  (2024-09-04T10:06:42Z)
• ShapeBoost: Boosting Human Shape Estimation with Part-Based Parameterization and Clothing-Preserving Augmentation [58.50613393500561]
  We propose ShapeBoost, a new human shape recovery framework. It achieves pixel-level alignment even for rare body shapes and high accuracy for people wearing different types of clothes.
  arXiv  Detail & Related papers  (2024-03-02T23:40:23Z)
• Accurate 3D Body Shape Regression using Metric and Semantic Attributes [55.58629009876271]
  We show that 3D body shape regression from images can be trained from easy-to-obtain anthropometric measurements and linguistic shape attributes. This is the first demonstration that 3D body shape regression from images can be trained from easy-to-obtain anthropometric measurements and linguistic shape attributes.
  arXiv  Detail & Related papers  (2022-06-14T17:54:49Z)
• Body Composition Estimation Based on Multimodal Multi-task Deep Neural Network [0.0]
  Body composition is largely made up of muscle, fat, bones, and water. We introduce a multimodal multi-task deep neural network to estimate body fat percentage and skeletal muscle mass.
  arXiv  Detail & Related papers  (2022-05-23T04:31:06Z)
• Probabilistic Estimation of 3D Human Shape and Pose with a Semantic Local Parametric Model [25.647676661390282]
  This paper addresses the problem of 3D human body shape and pose estimation from RGB images. We present a method that predicts distributions over local body shape in the form of semantic body measurements. We show that our method outperforms the current state-of-the-art in terms of identity-dependent body shape estimation accuracy.
  arXiv  Detail & Related papers  (2021-11-30T13:50:45Z)
• LatentHuman: Shape-and-Pose Disentangled Latent Representation for Human Bodies [78.17425779503047]
  We propose a novel neural implicit representation for the human body. It is fully differentiable and optimizable with disentangled shape and pose latent spaces. Our model can be trained and fine-tuned directly on non-watertight raw data with well-designed losses.
  arXiv  Detail & Related papers  (2021-11-30T04:10:57Z)
• 3D Human Body Reshaping with Anthropometric Modeling [59.51820187982793]
  Reshaping accurate and realistic 3D human bodies from anthropometric parameters poses a fundamental challenge for person identification, online shopping and virtual reality. Existing approaches for creating such 3D shapes often suffer from complex measurement by range cameras or high-end scanners. This paper proposes a novel feature-selection-based local mapping technique, which enables automatic anthropometric parameter modeling for each body facet.
  arXiv  Detail & Related papers  (2021-04-05T04:09:39Z)
• Synthetic Training for Accurate 3D Human Pose and Shape Estimation in the Wild [27.14060158187953]
  This paper addresses the problem of monocular 3D human shape and pose estimation from an RGB image. We propose STRAPS, a system that uses proxy representations, such as silhouettes and 2D joints, as inputs to a shape and pose regression neural network. We show that STRAPS outperforms other state-of-the-art methods on SSP-3D in terms of shape prediction accuracy.
  arXiv  Detail & Related papers  (2020-09-21T16:39:04Z)
• HEMlets PoSh: Learning Part-Centric Heatmap Triplets for 3D Human Pose and Shape Estimation [60.35776484235304]
  This work attempts to address the uncertainty of lifting the detected 2D joints to the 3D space by introducing an intermediate state-Part-Centric Heatmap Triplets (HEMlets) The HEMlets utilize three joint-heatmaps to represent the relative depth information of the end-joints for each skeletal body part. A Convolutional Network (ConvNet) is first trained to predict HEMlets from the input image, followed by a volumetric joint-heatmap regression.
  arXiv  Detail & Related papers  (2020-03-10T04:03:45Z)
• Anatomy-aware 3D Human Pose Estimation with Bone-based Pose Decomposition [92.99291528676021]
  Instead of directly regressing the 3D joint locations, we decompose the task into bone direction prediction and bone length prediction. Our motivation is the fact that the bone lengths of a human skeleton remain consistent across time. Our full model outperforms the previous best results on Human3.6M and MPI-INF-3DHP datasets.
  arXiv  Detail & Related papers  (2020-02-24T15:49:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.