video, fence, video repair, diminished reality (DR), structure from motion (SfM), light field rendering (LFR)
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.
Tsinghua University Press
Chanya Lueangwattana, Shohei Mori, Hideo Saito. Removing fences from sweep motion videos using global 3D reconstruction and fence-aware light field rendering. Computational Visual Media 2019, 5(1): 21-32.