DREAM: Diffusion Rectification and Estimation-Adaptive Models

Jinxin Zhou, Tianyu Ding, Tianyi Chen, Jiachen Jiang, Ilya Zharkov, Zhihui Zhu, Luming Liang; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024, pp. 8342-8351

We present DREAM a novel training framework representing Diffusion Rectification and Estimation-Adaptive Models requiring minimal code changes (just three lines) yet significantly enhancing the alignment of training with sampling in diffusion models. DREAM features two components: diffusion rectification which adjusts training to reflect the sampling process and estimation adaptation which balances perception against distortion. When applied to image super-resolution (SR) DREAM adeptly navigates the tradeoff between minimizing distortion and preserving high image quality. Experiments demonstrate DREAM's superiority over standard diffusion-based SR methods showing a to faster training convergence and a to reduction in necessary sampling steps to achieve comparable or superior results. We hope DREAM will inspire a rethinking of diffusion model training paradigms.