Conditional Consistency Guided Image Translation and Enhancement

TL;DR

This paper introduces Conditional Consistency Models (CCMs) that incorporate conditional inputs to improve multi-domain image translation and enhancement, demonstrating high-quality results across diverse datasets.

Contribution

The paper presents a novel conditional consistency framework for multi-domain image translation, extending consistency models with task-specific inputs for better structural preservation.

Findings

Effective across 10 datasets

Produces high-quality multi-domain translations

Outperforms existing methods in structural fidelity

Abstract

Consistency models have emerged as a promising alternative to diffusion models, offering high-quality generative capabilities through single-step sample generation. However, their application to multi-domain image translation tasks, such as cross-modal translation and low-light image enhancement remains largely unexplored. In this paper, we introduce Conditional Consistency Models (CCMs) for multi-domain image translation by incorporating additional conditional inputs. We implement these modifications by introducing task-specific conditional inputs that guide the denoising process, ensuring that the generated outputs retain structural and contextual information from the corresponding input domain. We evaluate CCMs on 10 different datasets demonstrating their effectiveness in producing high-quality translated images across multiple domains. Code is available at https://github.com/amilbhagat/Conditional-Consistency-Models.