# LOGAN: Unpaired Shape Transform in Latent Overcomplete Space

## TL;DR

LOGAN is a neural network that learns to transform shapes between unpaired domains by encoding shapes into a shared latent space and using GANs to generate realistic cross-domain shape transformations without requiring paired data.

## Contribution

The paper introduces LOGAN, a novel deep learning framework that performs unpaired shape transformations using an overcomplete latent space and adversarial training, without needing shape correspondences.

## Key findings

- LOGAN outperforms existing methods on unpaired shape translation tasks.
- The model effectively preserves shape features during transformation.
- LOGAN adapts to various shape domains, demonstrating versatility.

## Abstract

We introduce LOGAN, a deep neural network aimed at learning general-purpose shape transforms from unpaired domains. The network is trained on two sets of shapes, e.g., tables and chairs, while there is neither a pairing between shapes from the domains as supervision nor any point-wise correspondence between any shapes. Once trained, LOGAN takes a shape from one domain and transforms it into the other. Our network consists of an autoencoder to encode shapes from the two input domains into a common latent space, where the latent codes concatenate multi-scale shape features, resulting in an overcomplete representation. The translator is based on a generative adversarial network (GAN), operating in the latent space, where an adversarial loss enforces cross-domain translation while a feature preservation loss ensures that the right shape features are preserved for a natural shape transform. We conduct ablation studies to validate each of our key network designs and demonstrate superior capabilities in unpaired shape transforms on a variety of examples over baselines and state-of-the-art approaches. We show that LOGAN is able to learn what shape features to preserve during shape translation, either local or non-local, whether content or style, depending solely on the input domains for training.