pith. sign in

arxiv: 1801.07632 · v1 · pith:WG75WHDLnew · submitted 2018-01-23 · 💻 cs.CV · cs.GR

High Resolution Face Completion with Multiple Controllable Attributes via Fully End-to-End Progressive Generative Adversarial Networks

classification 💻 cs.CV cs.GR
keywords resolutioncompletionattributescontrollablefacehighmultipleadversarial
0
0 comments X
read the original abstract

We present a deep learning approach for high resolution face completion with multiple controllable attributes (e.g., male and smiling) under arbitrary masks. Face completion entails understanding both structural meaningfulness and appearance consistency locally and globally to fill in "holes" whose content do not appear elsewhere in an input image. It is a challenging task with the difficulty level increasing significantly with respect to high resolution, the complexity of "holes" and the controllable attributes of filled-in fragments. Our system addresses the challenges by learning a fully end-to-end framework that trains generative adversarial networks (GANs) progressively from low resolution to high resolution with conditional vectors encoding controllable attributes. We design novel network architectures to exploit information across multiple scales effectively and efficiently. We introduce new loss functions encouraging sharp completion. We show that our system can complete faces with large structural and appearance variations using a single feed-forward pass of computation with mean inference time of 0.007 seconds for images at 1024 x 1024 resolution. We also perform a pilot human study that shows our approach outperforms state-of-the-art face completion methods in terms of rank analysis. The code will be released upon publication.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Pose-variant 3D Facial Attribute Generation

    cs.CV 2019-07 unverdicted novelty 6.0

    A GAN-based method generates facial attributes directly on 3D face UV maps from posed images using texture completion and attribute synthesis networks, claiming better accuracy and identity preservation than prior 2D ...