A novel single-lead f-wave extraction algorithm based on the modern diffusion geometry data analysis framework is proposed.The algorithm is essentially an averaged beat subtraction algorithm, where the ventricular activity template is estimated by combining a newly designed metric, the 'diffusion distance', and the non-local Euclidean median based on the non-linear manifold setup. We coined the algorithm [Formula: see text].Two simulation schemes are considered, and the new algorithm [Formula: see text] outperforms traditional algorithms, including the average beat subtraction, principal component analysis, and adaptive singular value cancellation, in different evaluation metrics with statistical significance.The clinical potential is shown in the real Holter signal, and we introduce a new score to evaluate the performance of the algorithm.