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

Chanya Lueangwattana, Shohei Mori, Hideo Saito

研究成果: Article査読

1 被引用数 (Scopus)

抄録

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.

本文言語English
ページ(範囲)21-32
ページ数12
ジャーナルComputational Visual Media
5
1
DOI
出版ステータスPublished - 2019 3 1

ASJC Scopus subject areas

  • コンピュータ ビジョンおよびパターン認識
  • コンピュータ グラフィックスおよびコンピュータ支援設計
  • 人工知能

フィンガープリント

「Removing fences from sweep motion videos using global 3D reconstruction and fence-aware light field rendering」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル