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

Denis Rakitin, Ivan Shchekotov, Dmitry Vetrov
6/20/2024
cs.CVcs.LG
diffusion-flowdistillation

No confident code implementation found for this paper. 4 possible matches can be shown below.

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 4 weaker matches are hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Single-Step Bidirectional Unpaired Image Translation Using Implicit Bridge Consistency Distillation

85% match2025

Cross-Resolution Distribution Matching for Diffusion Distillation

84% match2026

Optimizing Distributional Geometry Alignment with Optimal Transport for Generative Dataset Distillation

83% match2025

Score Distillation of Flow Matching Models

83% match2025

Multistep Distillation of Diffusion Models via Moment Matching

82% match2024

EM Distillation for One-step Diffusion Models

82% match2024

Cite this paper

@article{rakitin2024regularized,
  title  = {Regularized Distribution Matching Distillation for One-step Unpaired Image-to-Image Translation},
  author = {Denis Rakitin and Ivan Shchekotov and Dmitry Vetrov},
  year   = {2024},
  eprint = {2406.14762},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2406.14762v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2406.14762.svg)](https://codeofpaper.com/paper/2406.14762)

Discussion