MGAPoseNet: multiscale graph-attention for 3D human pose estimation

Despite the considerable advancements made in the field of 3D human pose estimation from single-view images, previous studies have often overlooked the exploration of global and local correlations. Recognizing this limitation, we present MGAPoseNet, a novel network architecture meticulously designed to elevate the accuracy of 3D pose estimation. Our approach is distinguished by its simultaneous extraction of both local and global features, achieved through the parallel integration of Local Graph-based Joint Connection (LGC) and Global Attention-based Body Constraint (GAC) modules. Moreover, the performance of MGAPoseNet is further elevated by the sequential Spatial-Channel Graph MLP-Like Architecture (SC-GraphMLP) module. This module adeptly leverages spatial and channel information to model intricate interactions and dependencies among joint features, thereby refining the accuracy of pose estimation. Experimental evaluation conducted on benchmark datasets, including Human3.6M and MPI-INF-3DHP, unequivocally verifies the state-of-the-art performance of MGAPoseNet. This rigorous validation underscores its superiority in 3D human pose estimation tasks, while enhancing its coherence and clarity.