Scaling-up Disentanglement for Image Translation

by   Aviv Gabbay, et al.

Image translation methods typically aim to manipulate a set of labeled attributes (given as supervision at training time e.g. domain label) while leaving the unlabeled attributes intact. Current methods achieve either: (i) disentanglement, which exhibits low visual fidelity and can only be satisfied where the attributes are perfectly uncorrelated. (ii) visually-plausible translations, which are clearly not disentangled. In this work, we propose OverLORD, a single framework for disentangling labeled and unlabeled attributes as well as synthesizing high-fidelity images, which is composed of two stages; (i) Disentanglement: Learning disentangled representations with latent optimization. Differently from previous approaches, we do not rely on adversarial training or any architectural biases. (ii) Synthesis: Training feed-forward encoders for inferring the learned attributes and tuning the generator in an adversarial manner to increase the perceptual quality. When the labeled and unlabeled attributes are correlated, we model an additional representation that accounts for the correlated attributes and improves disentanglement. We highlight that our flexible framework covers multiple image translation settings e.g. attribute manipulation, pose-appearance translation, segmentation-guided synthesis and shape-texture transfer. In an extensive evaluation, we present significantly better disentanglement with higher translation quality and greater output diversity than state-of-the-art methods.


page 8

page 13

page 14

page 15

page 17

page 19

page 20

page 22


Exploring Unlabeled Faces for Novel Attribute Discovery

Despite remarkable success in unpaired image-to-image translation, exist...

Disentangled Unsupervised Image Translation via Restricted Information Flow

Unsupervised image-to-image translation methods aim to map images from o...

ELEGANT: Exchanging Latent Encodings with GAN for Transferring Multiple Face Attributes

Recent studies on face attribute transfer have achieved great success, e...

Training on Art Composition Attributes to Influence CycleGAN Art Generation

I consider how to influence CycleGAN, image-to-image translation, by usi...

A Unified Feature Disentangler for Multi-Domain Image Translation and Manipulation

We present a novel and unified deep learning framework which is capable ...

Adversarial Learning of Disentangled and Generalizable Representations for Visual Attributes

Recently, a multitude of methods for image-to-image translation has demo...

StyleT2I: Toward Compositional and High-Fidelity Text-to-Image Synthesis

Although progress has been made for text-to-image synthesis, previous me...

Please sign up or login with your details

Forgot password? Click here to reset