Open access
Sep 2026
DiMMPose: A Diffusion-Mamba Hybrid Framework with Multi-Prompt for Efficient and Robust 3D Human Pose Estimation
DiMMPose is proposed, a diffusion-based framework enhanced by Mamba’s state-space model for robust and efficient 3D pose estimation, which combines structured prompts encoded by LongCLIP with learnable prompt representations to provide anatomical and motion-related guidance during denoising.
Xu Li, Xue-Feng Guan, Chang Liu et al.
· Italian National Conference... · 0 citations