Abstract: Dynamic point cloud compression is essential for efficient 3D visual data transmission and storage. To achieve satisfactory coding efficiency, existing learning-based frameworks typically ...

Abstract: Traffic flow forecasting is challenging due to the intricate spatio-temporal correlations in traffic patterns. Previous works captured spatial dependencies based on graph neural networks and ...

Dynamic networks are networks that vary over time; their vertices are often not binary and instead represent a probability for having a link between two nodes. Statistical approaches or computer ...

This repository implements and compares various compression methods for multi-coil MRI data, evaluating their rate-distortion performance using PSNR and SSIM metrics computed on magnitude images.