Forward-only Diffusion Probabilistic Models
Forward-only Diffusion Probabilistic Models
This work presents a forward-only diffusion (FoD) approach for generative modelling. In contrast to traditional diffusion models that rely on a coupled forward-backward diffusion scheme, FoD directly learns data generation through a single forward diffusion process, yielding a simple yet efficient generative framework. The core of FoD is a state-dependent linear stochastic differential equation that involves a mean-reverting term in both the drift and diffusion functions. This mean-reversion property guarantees the convergence to clean data, naturally simulating a stochastic interpolation between source and target distributions. More importantly, FoD is analytically tractable and is trained using a simple stochastic flow matching objective, enabling a few-step non-Markov chain sampling during inference. The proposed FoD model, despite its simplicity, achieves competitive performance on various image-conditioned (e.g., image restoration) and unconditional generation tasks, demonstrating its effectiveness in generative modelling. Our code is available at https://github.com/Algolzw/FoD.
Ziwei Luo、Fredrik K. Gustafsson、Jens Sj?lund、Thomas B. Sch?n
计算技术、计算机技术
Ziwei Luo,Fredrik K. Gustafsson,Jens Sj?lund,Thomas B. Sch?n.Forward-only Diffusion Probabilistic Models[EB/OL].(2025-05-22)[2025-06-15].https://arxiv.org/abs/2505.16733.点此复制
评论