# ReshapeGAN: Object Reshaping by Providing A Single Reference Image

## TL;DR

ReshapeGAN is a versatile GAN architecture capable of reshaping objects in images to arbitrary shapes using a single reference, applicable across various datasets and problem settings, while preserving object appearance.

## Contribution

This work introduces ReshapeGAN, the first unified GAN framework for diverse object reshaping tasks, including cross-domain scenarios, with demonstrated superior results.

## Key findings

- Successfully reshapes objects across 8 tasks and 13 datasets.
- Preserves object appearance after reshaping.
- Outperforms state-of-the-art models in various metrics.

## Abstract

The aim of this work is learning to reshape the object in an input image to an arbitrary new shape, by just simply providing a single reference image with an object instance in the desired shape. We propose a new Generative Adversarial Network (GAN) architecture for such an object reshaping problem, named ReshapeGAN. The network can be tailored for handling all kinds of problem settings, including both within-domain (or single-dataset) reshaping and cross-domain (typically across mutiple datasets) reshaping, with paired or unpaired training data. The appearance of the input object is preserved in all cases, and thus it is still identifiable after reshaping, which has never been achieved as far as we are aware. We present the tailored models of the proposed ReshapeGAN for all the problem settings, and have them tested on 8 kinds of reshaping tasks with 13 different datasets, demonstrating the ability of ReshapeGAN on generating convincing and superior results for object reshaping. To the best of our knowledge, we are the first to be able to make one GAN framework work on all such object reshaping tasks, especially the cross-domain tasks on handling multiple diverse datasets. We present here both ablation studies on our proposed ReshapeGAN models and comparisons with the state-of-the-art models when they are made comparable, using all kinds of applicable metrics that we are aware of.