Back to Search Start Over

Regularized Distribution Matching Distillation for One-step Unpaired Image-to-Image Translation

Authors :
Rakitin, Denis
Shchekotov, Ivan
Vetrov, Dmitry
Publication Year :
2024

Abstract

Diffusion distillation methods aim to compress the diffusion models into efficient one-step generators while trying to preserve quality. Among them, Distribution Matching Distillation (DMD) offers a suitable framework for training general-form one-step generators, applicable beyond unconditional generation. In this work, we introduce its modification, called Regularized Distribution Matching Distillation, applicable to unpaired image-to-image (I2I) problems. We demonstrate its empirical performance in application to several translation tasks, including 2D examples and I2I between different image datasets, where it performs on par or better than multi-step diffusion baselines.

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2406.14762
Document Type :
Working Paper