Generative Motion In-betweening by Diffusion over Continuous Implicit Representations

ArXi:2605.12778v1 Announce Type: cross Recent advances in generative models have yielded impressive progress on motion in-betweening, allowing for complex, varied, and realistic motion transitions. However, recent methods still exhibit noticeable limitations in preserving keyframe information and ensuring motion continuity. In this paper, we propose a novel pipeline and sampling optimization strategy for latent diffusion models (LDM) based on motion implicit neural representations