• Home
  • Search
  • Inferring implicit 3D representations from human figures on pictorial maps
  • Cite Icon3
  • https://doi.org/10.1080/15230406.2023.2224063Copy DOI Icon

Inferring implicit 3D representations from human figures on pictorial maps

Show More
  • Abstract
  • Highlights & Summary
  • PDF
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

ABSTRACT In this work, we present an automated workflow to bring human figures, one of the most frequently appearing entities on pictorial maps, to the third dimension. Our workflow is based on training data and neural networks for single-view 3D reconstruction of real humans from photos. We first let a network consisting of fully connected layers estimate the depth coordinate of 2D pose points. The gained 3D pose points are inputted together with 2D masks of body parts into a deep implicit surface network to infer 3D signed distance fields (SDFs). By assembling all body parts, we derive 2D depth images and body part masks of the whole figure for different views, which are fed into a fully convolutional network to predict UV images. These UV images and the texture for the given perspective are inserted into a generative network to inpaint the textures for the other views. The textures are enhanced by a cartoonization network and facial details are resynthesized by an autoencoder. Finally, the generated textures are assigned to the inferred body parts in a ray marcher. We test our workflow with 12 pictorial human figures after having validated several network configurations. The created 3D models look generally promising, especially when considering the challenges of silhouette-based 3D recovery and real-time rendering of the implicit SDFs. Further improvement is needed to reduce gaps between the body parts and to add pictorial details to the textures. Overall, the constructed figures may be used for animation and storytelling in digital 3D maps.

Loading PDF

Similar Papers
  • Research Article
  • Citations6

An intelligent recommendation system for personalised parametric garment patterns by integrating designer’s knowledge and 3D body measurements

  • Mar 27, 2024
  • Ergonomics
  • Cheng Chi +3
  • Research Article
  • Citations8

Symbolic Immunity and Flexibility in Preschoolers' Human Figure Drawings

  • Sep 01, 1995
  • The Journal of Genetic Psychology
  • Chris J Boyatzis +2
  • Conference Article

CurveSDF: Binary Image Vectorization Using Signed Distance Fields

  • Jun 12, 2023
  • Zeqing Xia +1
  • Research Article
  • Citations2

A Review of Conversion Techniques for Typical 3D Model Representation Methods

  • Aug 04, 2025
  • Journal of Computer-Aided Design & Computer Graphics
  • Xiaolong Yin +2
  • Research Article
  • Citations17

Detection of Pictorial Map Objects with Convolutional Neural Networks

  • Sep 11, 2020
  • The Cartographic Journal
  • Raimund Schnürer +4
  • Conference Article
  • Citations35

Fuzzy neural expert system with automated extraction of fuzzy If-Then rules from a trained neural network

  • Dec 03, 1990
  • [1990] Proceedings. First International Symposium on Uncertainty Modeling and Analysis
  • Y Hayashi +1
  • Conference Article

Body Part Labelling with Minkowski Networks

  • Dec 01, 2019
  • Joseph Cahill-Lane +2
  • PDF
  • Book Chapter
  • Citations1

Bayesian Inference for Regularization and Model Complexity Control of Artificial Neural Networks in Classification Problems

  • Nov 23, 2023
  • Son T Nguyen +4
  • Research Article
  • Citations40

Human figure representation by blind children.

  • Jan 01, 1980
  • The Journal of General Psychology
  • Marcel Kinsbourne +1
  • Conference Article
  • Citations6

Improving human body part detection using deep learning and motion consistency

  • Nov 01, 2016
  • Manoj Ramanathan +2
  • PDF
  • Research Article
  • Citations3

Neural Vector Fields for Implicit Surface Representation and Inference

  • Oct 22, 2024
  • International Journal of Computer Vision
  • Edoardo Mello Rella +3
  • Conference Article

Reconstruction of Pilot Behaviour from Cockpit Image Recorder

  • Jan 05, 2020
  • AIAA Scitech 2020 Forum
  • Hiroka Tsuda +2
  • Research Article

Technology-assisted methods to assess the quality of the therapeutic alliance between health care providers and patients: a scoping review.

  • May 01, 2026
  • JBI evidence synthesis
  • Plaiphon Vaidyanuvatti +6
  • Research Article

ADAPT: AI‐Driven Artefact Purging Technique for IMU Based Motion Capture

  • Oct 17, 2024
  • Computer Graphics Forum
  • P Schreiner +4
  • Supplementary Content
  • Citations1

MetaAvatar: Learning Animatable Clothed Human Models from Few Depth Images

  • Jan 01, 2021
  • Repository for Publications and Research Data (ETH Zurich)
  • Shaofei Wang +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.