Deep learning-based artifacts removal in video compression

Title from PDF of title page viewed December 15, 2021Dissertation advisor: Zhu LiVitaIncludes bibliographical references (pages 112-129)Thesis (Ph.D.)--School of Computing and Engineering. University of Missouri--Kansas City, 2021The block-based coding structure in the hybrid video coding framework inevitably introduces compression artifacts such as blocking, ringing, etc. To compensate for those artifacts, extensive filtering techniques were proposed in the loop of video codecs, which are capable of boosting the subjective and objective qualities of reconstructed videos. Recently, neural network-based filters were presented with the power of deep learning from a large magnitude of data. Though the coding efficiency has been improved from traditional methods in High-Efficiency Video Coding (HEVC), the rich features and in- formation generated by the compression pipeline has not been fully utilized in the design of neural networks. Therefore, we propose a learning-based method to further improve the coding efficiency to its full extent. In addition, the point cloud is an essential format for three-dimensional (3-D) ob- jects capture and communication for Augmented Reality (AR) and Virtual Reality (VR) applications. In the current state of the art video-based point cloud compression (V-PCC),a dynamic point cloud is projected onto geometry and attribute videos patch by patch, each represented by its texture, depth, and occupancy map for reconstruction. To deal with oc- clusion, each patch is projected onto near and far depth fields in the geometry video. Once there are artifacts on the compressed two-dimensional (2-D) geometry video, they would be propagated to the 3-D point cloud frames. In addition, in the lossy compression, there always exists a tradeoff between the rate of bitstream and distortion (RD). Although some methods were proposed to attenuate these artifacts and improve the coding efficiency, the non-linear representation ability of Convolutional Neural Network (CNN) has not been fully considered. Therefore, we propose a learning-based approach to remove the geom- etry artifacts and improve the compressing efficiency. Besides, we propose using a CNN to improve the accuracy of the occupancy map video in V-PCC. To the best of our knowledge, these are the first learning-based solutions of the geometry artifacts removal in HEVC and occupancy map enhancement in V-PCC. The extensive experimental results show that the proposed approaches achieve significant gains in HEVC and V-PCC compared to the state-of-the-art schemes.Residual-Guided In-Loop Filter Using Convolution Neural Network -- Deep learning geometry compression artifacts removal for video-based point cloud compression -- Convolutional Neural Network-Based Occupancy Map Accuracy Improvement for Video-based Point Cloud Compressio