5 papers
DiffusionRVGE: Reinforcement Learning via Regression-Based Value Gradient Estimation
Jiayuan Wang, Tongyao Pang
Reinforcement learning improves diffusion models using rewards on generated images, but repeated denoising and gradient estimation make training expensive. We introduce \method, an…
A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
Zhaoqiang Liu, Tongyao Pang, Ruibing Wang +1
Pretrained diffusion models represent image distributions through a continuum of progressively smoothed distributions. This multiscale structure organizes generation from global st…
Forward-Evolution Error Analysis and Adaptive Design for Matrix-Valued Diffusion Models
Tongyao Pang, Zuowei Shen, Ruitong Zhang
Diffusion models learn to reverse a predefined corruption process, but sampling still requires a costly time discretization and depends on the chosen noise schedule. We study these…
Outlier-Robust Diffusion Solvers for Inverse Problems
Yang Zheng, Jiahua Liu, Tongyao Pang +2
Methods based on diffusion models (DMs) for solving inverse problems (IPs) have recently achieved remarkable performance. However, DM-based methods typically struggle against outli…
Enhancing Low-resolution Image Representation Through Normalizing Flows
Chenglong Bao, Tongyao Pang, Zuowei Shen +2
Low-resolution image representation can be regarded as a special form of sparse representation that retains only low-frequency information while discarding high-frequency component…