Fader Networks: Manipulating Images by Sliding Attributes

Abstract

This paper introduces a new encoder-decoder architecture that is trained to reconstruct images by disentangling the salient information of the image and the values of attributes directly in the latent space. As a result, after training, our model can generate different realistic versions of an input image by varying the attribute values. By using continuous attribute values, we can choose how much a specific attribute is perceivable in the generated image. This property could allow for applications where users can modify an image using sliding knobs, like faders on a mixing console, to change the facial expression of a portrait, or to update the color of some objects. Compared to the state-of-the-art which mostly relies on training adversarial networks in pixel space by altering attribute values at train time, our approach results in much simpler training schemes and nicely scales to multiple attributes. We present evidence that our model can significantly change the perceived value of the attributes while preserving the naturalness of images.

NIPS 2017

References in corpus (4)

• Deep Convolutional Inverse Graphics Network
• Invertible Conditional GANs for image editing
• Unsupervised Cross-Domain Image Generation
• Disentangling factors of variation in deep representations using adversarial training

Cited by in corpus (13)

• Driving-Signal Aware Full-Body Avatars
• Counterfactual State Explanations for Reinforcement Learning Agents via Generative Deep Learning
• 3D-A-Nets: 3D Deep Dense Descriptor for Volumetric Shapes with Adversarial Networks
• EEG-based Texture Roughness Classification in Active Tactile Exploration with Invariant Representation Learning Networks
• ImageEye: Batch Image Processing Using Program Synthesis
• Survey2Survey: A deep learning generative model approach for cross-survey image mapping
• Unsupervised 3D Reconstruction from a Single Image via Adversarial Learning
• Deepfake Video Forensics based on Transfer Learning
• A3T: Adversarially Augmented Adversarial Training
• DeepBlur: A Simple and Effective Method for Natural Image Obfuscation
• VAE/WGAN-Based Image Representation Learning For Pose-Preserving Seamless Identity Replacement In Facial Images
• Face Aging via Diffusion-based Editing
• TranSTYLer: Multimodal Behavioral Style Transfer for Facial and Body Gestures Generation