Zero-Pair Image to Image Translation using Domain Conditional Normalization

TL;DR

This paper introduces a domain conditional normalization method for zero-pair image translation, enabling translation between unpaired domains with improved performance and fewer parameters.

Contribution

It presents a novel domain conditional normalization technique that allows effective zero-pair image translation with a single generator and reduced model complexity.

Findings

Improved qualitative and quantitative translation results.

Effective translation between depth and semantic domains.

Fewer parameters needed compared to existing methods.

Abstract

In this paper, we propose an approach based on domain conditional normalization (DCN) for zero-pair image-to-image translation, i.e., translating between two domains which have no paired training data available but each have paired training data with a third domain. We employ a single generator which has an encoder-decoder structure and analyze different implementations of domain conditional normalization to obtain the desired target domain output. The validation benchmark uses RGB-depth pairs and RGB-semantic pairs for training and compares performance for the depth-semantic translation task. The proposed approaches improve in qualitative and quantitative terms over the compared methods, while using much fewer parameters. Code available at https://github.com/samarthshukla/dcn