![]() It also outperforms the end-to-end image compression networks by an average of 79.6% bitrate saving with much higher subjective quality and light field consistency. The whole encoder was designed to minimise its computational. The proposed method provides 2.137 times and 2.849 times higher compression efficiency relative to H.266/VVC and H.265/HEVC inter coding, respectively. image encoder 25,90 is a good example wich has been significantly improved. ![]() To train a stable and robust algorithm, a large-scale dataset consisting of 7549 light field images is proposed and built. Later you decide to compress the images to save your storage space, so you implement an image compression feature in the back-end. Different from the existing methods that exploit either spatial or angular consistency in the light field image, SADN decouples the angular and spatial information by dilation convolution and stride convolution in spatial-angular interaction, and performs feature fusion to compress spatial and angular information jointly. In this paper, we propose a novel end-to-end spatial-angular-decorrelated network (SADN) for high-efficiency light field image compression. Combined with minification and network compression, this usually leads to CSS files that are less than 10kB, even for large projects. Download a PDF of the paper titled SADN: Learned Light Field Image Compression with Spatial-Angular Decorrelation, by Kedeng Tong and 3 other authors Download PDF Abstract:Light field image becomes one of the most promising media types for immersive video applications.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |