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

• Main Authors: Chanya Lueangwattana, Shohei Mori, Hideo Saito
• Format: Article
• Language: English
• Published: SpringerOpen 2019-04-01
• Series: Computational Visual Media
• Subjects: video; fence; video repair; diminished reality (DR); structure from motion (SfM); light field rendering (LFR)
• Online Access: http://link.springer.com/article/10.1007/s41095-018-0126-8

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.