Multiple Exemplars-based Hallucinationfor Face Super-resolution and Editing

09/16/2020
by   Kaili Wang, et al.
0

Given a really low-resolution input image of a face (say 16x16 or 8x8 pixels), the goal of this paper is to reconstruct a high-resolution version thereof. This, by itself, is an ill-posed problem, as the high-frequency information is missing in the low-resolution input and needs to be hallucinated, based on prior knowledge about the image content. Rather than relying on a generic face prior, in this paper, we explore the use of a set of exemplars, i.e. other high-resolution images of the same person. These guide the neural network as we condition the output on them. Multiple exemplars work better than a single one. To combine the information from multiple exemplars effectively, we introduce a pixel-wise weight generation module. Besides standard face super-resolution, our method allows to perform subtle face editing simply by replacing the exemplars with another set with different facial features. A user study is conducted and shows the super-resolved images can hardly be distinguished from real images on the CelebA dataset. A qualitative comparison indicates our model outperforms methods proposed in the literature on the CelebA and WebFace dataset.

READ FULL TEXT

page 2

page 8

page 9

page 10

page 12

page 13

page 14

research
09/27/2019

Learning to Have an Ear for Face Super-Resolution

We propose a novel method to perform extreme (16x) face super-resolution...
research
09/21/2022

HAZE-Net: High-Frequency Attentive Super-Resolved Gaze Estimation in Low-Resolution Face Images

Although gaze estimation methods have been developed with deep learning ...
research
05/09/2020

High Resolution Face Age Editing

Face age editing has become a crucial task in film post-production, and ...
research
06/28/2018

Deep CNN Denoiser and Multi-layer Neighbor Component Embedding for Face Hallucination

Most of the current face hallucination methods, whether they are shallow...
research
04/02/2019

Guided Super-Resolution as a Learned Pixel-to-Pixel Transformation

Guided super-resolution is a unifying framework for several computer vis...
research
07/16/2022

Stochastic Attribute Modeling for Face Super-Resolution

When a high-resolution (HR) image is degraded into a low-resolution (LR)...
research
03/31/2022

MyStyle: A Personalized Generative Prior

We introduce MyStyle, a personalized deep generative prior trained with ...

Please sign up or login with your details

Forgot password? Click here to reset