DREAM: Diffusion Rectification and Estimation-Adaptive Models
Abstract
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.
Cite
Text
Zhou et al. "DREAM: Diffusion Rectification and Estimation-Adaptive Models." Conference on Computer Vision and Pattern Recognition, 2024. doi:10.1109/CVPR52733.2024.00797Markdown
[Zhou et al. "DREAM: Diffusion Rectification and Estimation-Adaptive Models." Conference on Computer Vision and Pattern Recognition, 2024.](https://mlanthology.org/cvpr/2024/zhou2024cvpr-dream/) doi:10.1109/CVPR52733.2024.00797BibTeX
@inproceedings{zhou2024cvpr-dream,
title = {{DREAM: Diffusion Rectification and Estimation-Adaptive Models}},
author = {Zhou, Jinxin and Ding, Tianyu and Chen, Tianyi and Jiang, Jiachen and Zharkov, Ilya and Zhu, Zhihui and Liang, Luming},
booktitle = {Conference on Computer Vision and Pattern Recognition},
year = {2024},
pages = {8342-8351},
doi = {10.1109/CVPR52733.2024.00797},
url = {https://mlanthology.org/cvpr/2024/zhou2024cvpr-dream/}
}