My camera can see through fences: A deep learning approach for image de-fencing
This addresses the issue of fence occlusion in images for amateur photographers, offering a more robust solution compared to conventional methods that are limited to static scenes.
The paper tackles the problem of removing fences from images, which obstruct amateur photography, by proposing a semi-automated algorithm using video of dynamic scenes and convolutional neural networks for fence detection, achieving qualitative and quantitative improvements over existing methods on datasets like PSU NRT and a new challenging one.
In recent times, the availability of inexpensive image capturing devices such as smartphones/tablets has led to an exponential increase in the number of images/videos captured. However, sometimes the amateur photographer is hindered by fences in the scene which have to be removed after the image has been captured. Conventional approaches to image de-fencing suffer from inaccurate and non-robust fence detection apart from being limited to processing images of only static occluded scenes. In this paper, we propose a semi-automated de-fencing algorithm using a video of the dynamic scene. We use convolutional neural networks for detecting fence pixels. We provide qualitative as well as quantitative comparison results with existing lattice detection algorithms on the existing PSU NRT data set and a proposed challenging fenced image dataset. The inverse problem of fence removal is solved using split Bregman technique assuming total variation of the de-fenced image as the regularization constraint.