Light Field Compression Based on Graph Sample and Aggregaet Algorithm

The application of light field technology has gained increasing attention owing to its remarkable ability to capture highdimensional scene information. However, the storage and transmission of the substantial amount of data generated by this technology pose significant challenges. To address this issue, we present a novel approach that utilizes the Graph sample and aggregate algorithm (GraphSAGE), a potent graph neural network model that learns node embeddings on graphs. Our method represents each view of the light field as a node in a graph and uses GraphSAGE to acquire a compressed set of node embeddings that effectively capture the light field. To evaluate our approach, we compare it against the state-of-the-art light field compression methods, including HEVC, Graph learning methods, and our previous work. Our experimental results demonstrate that our proposed approach achieves highly competitive compression performance when compared to these state-of-the-art methods.