COT Flow: Learning Optimal-Transport Image Sampling and Editing by Contrastive Pairs

TL;DR

COT Flow is a novel image sampling and editing method using optimal transport that enables fast, high-quality, and flexible zero-shot image translation and editing without the limitations of traditional diffusion models.

Contribution

It introduces a new optimal transport-based flow method that improves sampling speed, editing flexibility, and unpaired image translation capabilities over existing diffusion models.

Findings

Generates competitive quality images in one step.

Enables unpaired image-to-image translation without prior distribution constraints.

Provides flexible user-guided editing with high quality.

Abstract

Diffusion models have demonstrated strong performance in sampling and editing multi-modal data with high generation quality, yet they suffer from the iterative generation process which is computationally expensive and slow. In addition, most methods are constrained to generate data from Gaussian noise, which limits their sampling and editing flexibility. To overcome both disadvantages, we present Contrastive Optimal Transport Flow (COT Flow), a new method that achieves fast and high-quality generation with improved zero-shot editing flexibility compared to previous diffusion models. Benefiting from optimal transport (OT), our method has no limitation on the prior distribution, enabling unpaired image-to-image (I2I) translation and doubling the editable space (at both the start and end of the trajectory) compared to other zero-shot editing methods. In terms of quality, COT Flow can generate competitive results in merely one step compared to previous state-of-the-art unpaired image-to-image (I2I) translation methods. To highlight the advantages of COT Flow through the introduction of OT, we introduce the COT Editor to perform user-guided editing with excellent flexibility and quality. The code will be released at https://github.com/zuxinrui/cot_flow.