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.
Code (1)
Tasks
Conditional Image GenerationImage DehazingImage GenerationImage RestorationLow-Light Image EnhancementSingle Image DerainingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
PRISM: Probabilistic and Robust Inverse Solver with Measurement-Conditioned Diffusion Prior for Blind Inverse Problems
Diffusion models are now commonly used to solve inverse problems in computational imaging. However, most diffusion-based inverse solvers require complete knowledge of the forward operator to be used. In this work, we int…
Image DeblurringAn explicit formulation of the learned noise predictor $ε_θ({\bf x}_t, t)$ via the forward-process noise $ε_{t}$ in denoising diffusion probabilistic models (DDPMs)
In denoising diffusion probabilistic models (DDPMs), the learned noise predictor $ ε_θ ( {\bf x}_t , t)$ is trained to approximate the forward-process noise $ε_t$. The equality $\nabla_{{\bf x}_t} \log q({\bf x}_t) = -\f…
ShiftDDPMs: Exploring Conditional Diffusion Models by Shifting Diffusion Trajectories
Diffusion models have recently exhibited remarkable abilities to synthesize striking image samples since the introduction of denoising diffusion probabilistic models (DDPMs). Their key idea is to disrupt images into nois…
DenoisingImage GenerationTruncated Diffusion Probabilistic Models and Diffusion-based Adversarial Auto-Encoders
Employing a forward diffusion chain to gradually map the data to a noise distribution, diffusion-based generative models learn how to generate the data by inferring a reverse diffusion chain. However, this approach is sl…
Image GenerationText-to-Image GenerationAnisotropic Diffusion Probabilistic Model for Imbalanced Image Classification
Real-world data often has a long-tailed distribution, where the scarcity of tail samples significantly limits the model's generalization ability. Denoising Diffusion Probabilistic Models (DDPM) are generative models base…
ClassificationDenoisingimage-classificationImage Classification+2