Abstract
In public spaces such as zoos and sports facilities, the presence of fences often annoys tourists and professional photographers. There is a demand for a post-processing tool to produce a non-occluded view from an image or video. This “de-fencing” task is divided into two stages: one to detect fence regions and the other to fill the missing part. For over a decade, various methods have been proposed for video-based de-fencing. However, only a few single-image-based methods are proposed. In this paper, we focus on single-image fence removal. Conventional approaches suffer from inaccurate and non-robust fence detection and inpainting due to less content information. To solve these problems, we combine novel methods based on a deep convolutional neural network (CNN) and classical domain knowledge in image processing. In the training process, we are required to obtain both fence images and corresponding non-fence ground truth images. Therefore, we synthesize natural fence images from real images. Moreover, spacial filtering processing (e.g. a Laplacian filter and a Gaussian filter) improves the performance of the CNN for detection and inpainting. Our proposed method can automatically detect a fence and generate a clean image without any user input. Experimental results demonstrate that our method is effective for a broad range of fence images.
Highlights
Image de-fencing, the process of removing a fence from an image, is an important problem
Robust and automatic fence removal methods are required for a variety of applications
IMAGE-BASED FENCE REMOVAL On the other hand, image-based de-fencing methods are more challenging because we have less information to detect fence regions and to fill-in the hidden part
Summary
Image de-fencing, the process of removing a fence from an image, is an important problem. Single-image fence removal task is thought to be more challenging due to less information To address this problem, we combine a deep CNN and classical domain knowledge in image processing. B. IMAGE-BASED FENCE REMOVAL On the other hand, image-based de-fencing methods are more challenging because we have less information to detect fence regions and to fill-in the hidden part. That is based on the assumption that learning the residual mapping is simpler than directly learning the mapping between the output and the input This Residual-learning-based approach can solve several CNN problems and succeed in several image restoration tasks [20], [21]. This paper makes the following three contributions: 1) By combining novel CNN methods and classical image processing techniques, our proposed network can automatically detect fence regions and recover the hidden background without any user intervention.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
