Automatic Objects Removal for Scene Completion
This addresses the challenge of object occlusion in photo streams for big data applications like 3D scene reconstruction, though it appears incremental as it builds on existing image completion techniques.
The paper tackles the problem of removing occluding foreground objects from unaligned and uncalibrated photos to aid in 3D scene reconstruction, proposing a structure-based image completion algorithm that uses edge matching and texture synthesis to produce visually plausible results, with experimental evaluation showing satisfactory performance for applications like 3D reconstruction and location recognition.
With the explosive growth of web-based cameras and mobile devices, billions of photographs are uploaded to the internet. We can trivially collect a huge number of photo streams for various goals, such as 3D scene reconstruction and other big data applications. However, this is not an easy task due to the fact the retrieved photos are neither aligned nor calibrated. Furthermore, with the occlusion of unexpected foreground objects like people, vehicles, it is even more challenging to find feature correspondences and reconstruct realistic scenes. In this paper, we propose a structure based image completion algorithm for object removal that produces visually plausible content with consistent structure and scene texture. We use an edge matching technique to infer the potential structure of the unknown region. Driven by the estimated structure, texture synthesis is performed automatically along the estimated curves. We evaluate the proposed method on different types of images: from highly structured indoor environment to the natural scenes. Our experimental results demonstrate satisfactory performance that can be potentially used for subsequent big data processing: 3D scene reconstruction and location recognition.