Video Inpainting of Occluding and Occluded Objects

Abstract

The authors present a basic technique to fill in missing parts of a video sequence taken from a static camera. Two important cases are considered. The first case is concerned with the removal of nonstationary objects that occlude a stationary background. For this problem the authors use a priority-based spatio-temporal synthesis scheme for inpainting the stationary background. The second and more difficult case involves filling in moving objects when they are partially occluded. For this problem they propose a priority scheme to first inpaint the occluded moving objects, and then fill in the remaining area with stationary background using the method proposed for the first case. They use as input an optical-flow based mask, which tells them if an undamaged pixel is moving or is stationary. The moving object is inpainted by copying patches from undamaged frames, and this copying is independent of the background of the moving object in either frame. This work has applications in a variety of different areas, including video special effects and the restoration and enhancement of damaged videos. The examples shown in the paper illustrate these ideas.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 2005
Accession Number
ADA437289

Entities

People

  • Guillermo Sapiro
  • Kedar A. Patwardhan
  • Marcelo Bertalmio

Organizations

  • University of Minnesota

Tags

Communities of Interest

  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Abstracts
  • Algorithms
  • Computations
  • Consistency
  • Equations
  • Gray Scale
  • Information Operations
  • Low Resolution
  • Mathematics
  • Military Research
  • Minnesota
  • Sequences
  • Stationary
  • Three Dimensional
  • Video
  • Video Frames

Readers

  • Computer Vision.