Title: Real Time Edit Propagation by Efficient Sampling

Speaker: Prof. Wencheng Wang (State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences)

Time: 10:00am, October 12th (Wednesday), 2011.

Venue: Lecture Room, Level 3, Building No. 5, State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences

Abstract:

A recent work of ours is introduced in this seminar. It is on adjusting the appearance of images to meet the user's desire. Generally, it is popular to edit the appearance of images using strokes, owing to their ease of use and convenience of conveying the user’s intention. However, propagating the user inputs to the rest of the images requires solving an enormous optimization problem, which is very time consuming, thus preventing its practical use. In this work, a two-step edit propagation scheme is proposed, first to solve edits on clusters of similar pixels and then to interpolate individual pixel edits from cluster edits. The key in our scheme is that we use efficient stroke sampling to compute the affinity between image pixels and strokes. Based on this, our clustering does not need to be stroke-adaptive and thus the number of clusters is greatly reduced, resulting in a significant speedup. The proposed method has been tested on various images, and the results show that it is more than one order of magnitude faster than existing methods, while still achieving precise results compared with the ground truth. Moreover, its efficiency is not sensitive to the number of strokes, making it suitable for performing dense edits in practice.