Search

In this paper, we propose a new face relighting algorithm powered by a large database of face images captured under various known lighting conditions (a Multi-PIE database). Key insight of our algorithm is that a face can be represented by an assemble of patches from many other faces. The algorithm finds the most similar face patches in the database in terms of the lighting and the appearance. By assembling the matched patches, we can visualize the input face under various lighting conditions. Unlike existing face relighting algorithms, we neither use any kinds of face model nor make a physical assumption. Instead, our algorithm is a data-driven approach, synthesizing the appearance of the image patch using the appearance of the example patch. Using a data-driven approach, we can account for various intrinsic facial features including the non-Lambertian skin properties as well as the hair. Also, our algorithm is insensitive to the face misalignment. We demonstrate the performance of our algorithm by face relighting and face recognition experiments. Especially, the synthesized results show that the proposed algorithm can successfully handle various intrinsic features of an input face. Also, from the face recognition experiment, we show that our method is comparable to the most recent face relighting work.

Time-of-flight cameras produce 3D geometry enabling faster and easier 3D scene capturing. The depth camera, however, suffers from motion blurs when the movement from either camera or scene appears. Unlike other noises, depth motion blur is hard to eliminate by any general filtering methods and yields the serious distortion in 3D reconstruction, typically causing uneven object boundaries and blurs. In this paper, we provide a through analysis on the ToF depth motion blur and a modeling method which is used to detect a motion blur region from a depth image. We show that the proposed method correctly detects blur regions using the set of all possible motion artifact models.