[Submitted on 11 Jun 2024 (v1), last revised 11 Oct 2026 (this version, v3)]
Abstract:Human motion generation is a challenging task due to its high dimensionality and the difficulty of generating fine-grained motions. Diffusion methods have been proposed due to their high sample quality and expressiveness. Early approaches treat the entire sequence as a whole, which is computationally expensive and restricts sequence length. In contrast, autoregressive diffusion models generate longer sequences. However, their reliance on fully denoising previous frames complicates training and inference. Consequently, we propose RDM, a new recurrent diffusion formulation inspired by Recurrent Neural Networks (RNNs). RDM explicitly conditions the diffusion process on preceding noisy frames, avoiding the cost of full denoising. To overcome the challenge of maintaining its probabilistic nature, we employ Normalizing Flows to model recurrent connections. Our evaluations demonstrate RDM’s effectiveness: it achieves comparable performance to autoregressive baselines and generates long sequences that remain aligned with the text. RDM also skips diffusion steps during inference, reducing computational cost by up to 18x over autoregressive baselines. Project page: this https URL.
Submission history
From: Mirgahney Mohamed Mr [view email]
[v1] Tue, 11 Jun 2024 11:25:37 UTC (4,444 KB)
[v2] Sun, 8 Mar 2026 17:54:16 UTC (5,905 KB)
[v3] Sun, 11 Oct 2026 23:24:49 UTC (14,722 KB)
