Removing fences from sweep motion videos using global 3D reconstruction and fence-aware light field rendering

Chanya Lueangwattana, Shohei Mori, Hideo Saito

Research output: Contribution to journalArticle

Abstract

Diminishing the appearance of a fence in an image is a challenging research area due to the characteristics of fences (thinness, lack of texture, etc.) and the need for occluded background restoration. In this paper, we describe a fence removal method for an image sequence captured by a user making a sweep motion, in which occluded background is potentially observed. To make use of geometric and appearance information such as consecutive images, we use two well-known approaches: structure from motion and light field rendering. Results using real image sequences show that our method can stably segment fences and preserve background details for various fence and background combinations. A new video without the fence, with frame coherence, can be successfully provided.

Original languageEnglish
JournalComputational Visual Media
DOIs
Publication statusAccepted/In press - 2018 Jan 1

    Fingerprint

Keywords

  • diminished reality (DR)
  • fence
  • light field rendering (LFR)
  • structure from motion (SfM)
  • video
  • video repair

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Computer Graphics and Computer-Aided Design
  • Artificial Intelligence

Cite this