Capturing Dynamic Textured Surfaces of Moving Targets

Abstract

We present an end-to-end system for reconstructing complete watertight and textured models of moving subjects such as clothed humans and animals, using only three or four handheld sensors. The heart of our framework is a new pairwise registration algorithm that minimizes, using a particle swarm strategy, an alignment error metric based on mutual visibility and occlusion. We show that this algorithm reliably registers partial scans with as little as 15 % overlap without requiring any initial correspondences, and outperforms alternative global registration algorithms. This registration algorithm allows us to reconstruct moving subjects from free-viewpoint video produced by consumer-grade sensors, without extensive sensor calibration, constrained capture volume, expensive arrays of cameras, or templates of the subject geometry.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Sep 16, 2016
Accession Number
AD1158065

Entities

People

  • Duygu Ceylan
  • Etienne Vouga
  • Gerard Medioni
  • Hao Li
  • Lingyu Wei
  • Qixing Huang
  • Ruizhe Wang

Organizations

  • Adobe
  • Toyota Technological Institute at Chicago
  • University of Texas at Austin

Tags

Communities of Interest

  • Energy and Power Technologies
  • Sensors

DTIC Thesaurus Topics

  • Algorithms
  • Artificial Intelligence Software
  • Computational Science
  • Computer Graphics
  • Computer Vision
  • Data Sets
  • Geometry
  • Graphics
  • Image Registration
  • Intelligence Community (United States)
  • Materials
  • Moving Targets
  • Neural Networks
  • New York
  • Particle Swarm Optimization
  • Three Dimensional
  • Virtual Reality

Fields of Study

  • Computer science

Readers

  • Agent-Based Social Robotics and Mobile-Assisted Learning in Virtual Environments.
  • Computer Vision.