# An Unpaired Shape Transforming Method for Image Translation and Cross-Domain Retrieval

## TL;DR

This paper introduces an unpaired geometric image translation method that transfers object shapes across domains while maintaining appearance, trained without paired data, and useful for cross-domain retrieval.

## Contribution

The proposed model performs shape transfer within a single unpaired training framework without post-processing, advancing geometric image translation methods.

## Key findings

- Effective shape transfer demonstrated on multiple datasets.
- Features learned are useful for cross-domain item retrieval.
- Model operates without paired training data or post-processing.

## Abstract

We address the problem of unpaired geometric image-to-image translation. Rather than transferring the style of an image as a whole, our goal is to translate the geometry of an object as depicted in different domains while preserving its appearance characteristics. Our model is trained in an unpaired fashion, i.e. without the need of paired images during training. It performs all steps of the shape transfer within a single model and without additional post-processing stages. Extensive experiments on the VITON, CMU-Multi-PIE and our own FashionStyle datasets show the effectiveness of the method. In addition, we show that despite their low-dimensionality, the features learned by our model are useful to the item retrieval task.