Zero-Pair Image to Image Translation using Domain Conditional Normalization
This addresses a specific problem in computer vision for tasks like depth-semantic translation, but it is incremental as it builds on existing unpaired translation methods.
The paper tackles zero-pair image-to-image translation between domains without direct paired data by using domain conditional normalization, achieving improved qualitative and quantitative performance with fewer parameters.
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