Robust object removal with an exemplar-based image inpainting approach

2014 ◽  
Vol 123 ◽  
pp. 150-155 ◽  
Author(s):  
Jing Wang ◽  
Ke Lu ◽  
Daru Pan ◽  
Ning He ◽  
Bing-kun Bao
Keyword(s):  
Image Inpainting ◽  
Object Removal

scholarly journals A Detection Approach Using LSTM-CNN for Object Removal Caused by Exemplar-Based Image Inpainting

Electronics ◽  
2020 ◽  
Vol 9 (5) ◽  
pp. 858
Author(s):  
Ming Lu ◽  
Shaozhang Niu
Keyword(s):  
False Alarm ◽  
False Alarm Rate ◽  
Short Term Memory ◽  
Image Inpainting ◽  
Learning Ability ◽  
Post Processing ◽  
Object Removal ◽  
Combined Operations ◽  
Detection Approach ◽  
Lstm Network

Exemplar-based image inpainting technology is a “double-edged sword”. It can not only restore the integrity of image by inpainting damaged or removed regions, but can also tamper with the image by using the pixels around the object region to fill in the gaps left by object removal. Through the research and analysis, it is found that the existing exemplar-based image inpainting forensics methods generally have the following disadvantages: the abnormal similar patches are time-consuming and inaccurate to search, have a high false alarm rate and a lack of robustness to multiple post-processing combined operations. In view of the above shortcomings, a detection method based on long short-term memory (LSTM)-convolutional neural network (CNN) for image object removal is proposed. In this method, CNN is used to search for abnormal similar patches. Because of CNN’s strong learning ability, it improves the speed and accuracy of the search. The LSTM network is used to eliminate the influence of false alarm patches on detection results and reduce the false alarm rate. A filtering module is designed to eliminate the attack of post-processing operation. Experimental results show that the method has a high accuracy, and can resist the attack of post-processing combination operations. It can achieve a better performance than the state-of-the-art approaches.

scholarly journals An image inpainting method for object removal based on difference degree constraint

2020 ◽  
Author(s):  
Lei Zhang ◽  
Minhui Chang
Keyword(s):  
Source Region ◽  
Image Inpainting ◽  
Mismatch Error ◽  
Matching Rule ◽  
Target Region ◽  
Object Removal ◽  
Degree Constraint ◽  
Mean Differences ◽  
Degree Of Similarity ◽  
Restoration Effect

Abstract In the inpainting method for object removal, SSD (Sum of Squared Differences) is commonly used to measure the degree of similarity between the exemplar patch and the target patch, which has a very important impact on the restoration results. Although the matching rule is relatively simple, it is likely to lead to the occurrence of mismatch error. Even worse, the error may be accumulated along with the process continues. Finally some unexpected objects may be introduced into the target region, making the result unable to meet the requirements of visual consistency. In view of these problems, we propose an inpainting method for object removal based on difference degree constraint. Firstly, we define the MSD (Mean of Squared Differences) and use it to measure the degree of differences between corresponding pixels at known positions in the target patch and the exemplar patch. Secondly, we define the SMD (Square of Mean Differences) and use it to measure the degree of differences between the pixels at known positions in the target patch and the pixels at unknown positions in the exemplar patch. Thirdly, based on MSD and SMD, we define a new matching rule and use it to find the most similar exemplar patch in the source region. Finally, we use the exemplar patch to restore the target patch. Experimental results show that the proposed method can effectively prevent the occurrence of mismatch error and improve the restoration effect.

Region Filling and Object Removal by Exemplar-Based Image Inpainting

2004 ◽  
Vol 13 (9) ◽  
pp. 1200-1212 ◽  
Author(s):  
A. Criminisi ◽  
P. Perez ◽  
K. Toyama
Keyword(s):  
Image Inpainting ◽  
Object Removal ◽  
Region Filling

scholarly journals Generative multiview inpainting for object removal in large indoor spaces

2021 ◽  
Vol 18 (2) ◽  
pp. 172988142199654
Author(s):  
Joohyung Kim ◽  
Janghun Hyeon ◽  
Nakju Doh
Keyword(s):  
Large Scale ◽  
Image Inpainting ◽  
Point Clouds ◽  
Target Object ◽  
Data Sets ◽  
Learning Approaches ◽  
Multiple Images ◽  
Object Removal ◽  
Image Planes ◽  
Indoor Spaces

As interest in image-based rendering increases, the need for multiview inpainting is emerging. Despite of rapid progresses in single-image inpainting based on deep learning approaches, they have no constraint in obtaining color consistency over multiple inpainted images. We target object removal in large-scale indoor spaces and propose a novel pipeline of multiview inpainting to achieve color consistency and boundary consistency in multiple images. The first step of the pipeline is to create color prior information on masks by coloring point clouds from multiple images and projecting the colored point clouds onto the image planes. Next, a generative inpainting network accepts a masked image, a color prior image, imperfect guideline, and two different masks as inputs and yields the refined guideline and inpainted image as outputs. The color prior and guideline input ensure color and boundary consistencies across multiple images. We validate our pipeline on real indoor data sets quantitatively using consistency distance and similarity distance, metrics we defined for comparing results of multiview inpainting and qualitatively.

scholarly journals Object Removal using a New Exemplar-Based Image Inpainting Algorithm and Seam Carving

2019 ◽  
Vol 8 (4) ◽  
pp. 9186-9191
Keyword(s):  
Texture Synthesis ◽  
Image Inpainting ◽  
Seam Carving ◽  
Target Region ◽  
Object Removal ◽  
Proposed Model ◽  
Priority Function ◽  
Removal Technique

This paper proposed a new object removal techniques based on exemplar-based technique and seam carving. Exemplar- based inpainting technique has been a point of attraction due to its moderate computational task an its performance. Moreover in this paper object removal technique for image based on discontinuous by seam carving has been introduced. Image inpainting is an approach fro restoring the damage part of an image in reference to the information from the undamaged part to make the restored image continuous, natural and to look complete. In this method patches are used to fill the target region in the image. Both texture synthesis and structure propagation are used simultaneously. Here robust exemplar method has been used avoiding dropping effect by using robust priority function. We have also used seam-carving for object removal. The PSNR values of the proposed model have been calculated and is also compared with the previous techniques’ results.

Sign in / Sign up

Export Citation Format

Share Document