Interactive Normal Reconstruction from a Single Image
Computer Graphics and Modern Art
Our goal is to reconstruct a 3D surface from a single image. This operation is important for modeling and processing software. Our approach consists of two parts. First, we introduce a novel shape-from-shading algorithm (SfS) that produces faithful normal reconstruction for local image region (high-frequency component), but it fails to faithfully recover the overall global structure (low-frequency component). Our second contribution consists of an approach that corrects low frequency error using a simple markup procedure. Combining these two approaches, we can produce high-quality surfaces quickly from single images.
In this project we will develop
algorithm and create an application.