Pre-filtering with locally adaptive filter set for reference frame in video compression

Abstract

To reduce temporal redundancy, conventional video coding standards, such as H.264/AVC, use block based motion estimation (ME) and compensation algorithm. However, the coding performance of H.264/AVC significantly drops when characteristics of video contents are changed due to the motion. In this paper, we proposed a pre-filtering algorithm with locally adaptive filter set for the reference frame to minimize the prediction error in the ME process. With image statistics, we adaptively construct a pre-filter set and apply the pre-filter set to the reference frame locally. The proposed algorithm is more efficient in sequences that have high resolution or fast motion. By manipulating the reference frame similar to the current frame, the coding performance is significantly improved. Compared with H.264/AVC, the proposed algorithm achieves bit-rate reduction up to 15.28%.