Abstract
While taking photographs, we often face the problem that unwanted foreground objects (e.g., vehicles, signs, and pedestrians) occlude the main subject(s). We propose to apply image interpolation (also known as inpainting) techniques to remove unwanted objects in the photographs and to automatically patch the vacancy after the unwanted objects are removed. When given only a single image, if the information loss after the unwanted objects in images being removed is too great, the patching results are usually unsatisfactory. The proposed inpainting techniques employ the homographic constraints in geometry to incorporate multiple images taken from different viewpoints. Our experiment results showed that the proposed techniques could effectively reduce process in searching for potential patches from multiple input images and decide the best patches for the missing regions.
Highlights
Historical sites represent the culture of a country
The process to patch the vacancy after unwanted objects are removed is commonly referred as image inpainting and texture synthesis in the literature [8,9,10,11]
When the image information loss is too great after object removal, the patching results are usually undesirable
Summary
Historical sites represent the culture of a country. As a result, preserving historical sites becomes a more and more important trend in recent years. Image inpainting is the process to remove unwanted objects in the photographs and to patch the vacancy. The usual solution is to employ image inpainting previously proposed [1,2,3,4,5,6,7] to remove the unwanted trees and cars, and patch the vacancy left behind. The process to patch the vacancy after unwanted objects are removed is commonly referred as image inpainting and texture synthesis in the literature [8,9,10,11]. We first apply the homography property to solve the point correspondence problem among multiple images taken from different viewpoints for image inpainting. Our main contribution is to propose an automatic image interpolation algorithm for image inpainting
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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 call
