Identity and Attribute Preserving Thumbnail Upscaling

TL;DR

This paper introduces a novel method for upscaling low-resolution face thumbnails into high-resolution images that accurately preserve identity, race, and facial attributes, addressing biases and fidelity issues of prior methods.

Contribution

The authors propose an augmented feature extractor and a new generation process that jointly preserves identity, race, and facial attributes during image upscaling.

Findings

Improved face similarity recognition accuracy.

Enhanced preservation of race and facial attributes.

Better generation of high-resolution images maintaining input identity.

Abstract

We consider the task of upscaling a low resolution thumbnail image of a person, to a higher resolution image, which preserves the person's identity and other attributes. Since the thumbnail image is of low resolution, many higher resolution versions exist. Previous approaches produce solutions where the person's identity is not preserved, or biased solutions, such as predominantly Caucasian faces. We address the existing ambiguity by first augmenting the feature extractor to better capture facial identity, facial attributes (such as smiling or not) and race, and second, use this feature extractor to generate high-resolution images which are identity preserving as well as conditioned on race and facial attributes. Our results indicate an improvement in face similarity recognition and lookalike generation as well as in the ability to generate higher resolution images which preserve an input thumbnail identity and whose race and attributes are maintained.