Beyond Sparse Keypoints: Dense Pose Modeling for Robust Gait Recognition (ACM MM 2025 🗣️Oral)

Left: Motivation of DPGait approach.          Right: Visualization of dense points.

This is the offical implementation of our paper represented on ACM MM 2025: We propose DPGait, a dense pose-based method to solve the limitations of sparse keypoints. On the upstream, we extend estimation model to output human dense points. On the downstream, we design a divide-and-conquer modeling architecture. Our method achieves SOTA performance across three datasets, demonstrating the effectiveness of method in complex scenarios.

• Code Release
• Model Release