Preprint
Oct 2026
DSR-Net: Learning Dynamic Skeletal Relations for 3D Human Pose Estimation
3D human pose estimation requires accurate modeling of motion-dependent skeletal structures and inter-joint dependencies. Existing methods typically rely on fixed skeletal topologies in Graph Convolutional Networks (GCNs) or implicitly capture joint relations through attention mechanisms, limiting their adaptability to...
Fan Li, Jian Xiang, Lin-Lin Xue et al.
· 0 citations