LOGAN: Unpaired Shape Transform in Latent Overcomplete Space

SIGGRAPH Asia 2019
Kangxue Yin Zhiqin Chen Hui Huang Daniel Cohen-Or Hao Zhang


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.

paper supplementary data code


@article {yin2019logan,
    author = {Kangxue Yin and Zhiqin Chen and Hui Huang and Daniel Cohen-Or and Hao Zhang}
    title = {LOGAN: Unpaired Shape Transform in Latent Overcomplete Space}
    journal = {ACM Transactions on Graphics(Special Issue of SIGGRAPH Asia)}
    volume = {38}
    number = {6}
    pages = {198:1--198:13}
    year = {2019}