Super-Resolving Cross-Domain Face Miniatures by Peeking at One-Shot Exemplar

TL;DR

This paper introduces DAP-FSR, a novel domain-aware super-resolution network that adapts to target domains using only one exemplar, significantly improving face super-resolution across different lighting and hardware conditions.

Contribution

The paper presents the first method to adapt face super-resolution models to a new domain with only a single high-resolution and low-resolution exemplar, leveraging latent space mixing for domain adaptation.

Findings

Outperforms state-of-the-art methods on three benchmarks.

Effectively reduces domain gap with minimal exemplar data.

Generates high-quality, style-consistent super-resolved faces.

Abstract

Conventional face super-resolution methods usually assume testing low-resolution (LR) images lie in the same domain as the training ones. Due to different lighting conditions and imaging hardware, domain gaps between training and testing images inevitably occur in many real-world scenarios. Neglecting those domain gaps would lead to inferior face super-resolution (FSR) performance. However, how to transfer a trained FSR model to a target domain efficiently and effectively has not been investigated. To tackle this problem, we develop a Domain-Aware Pyramid-based Face Super-Resolution network, named DAP-FSR network. Our DAP-FSR is the first attempt to super-resolve LR faces from a target domain by exploiting only a pair of high-resolution (HR) and LR exemplar in the target domain. To be specific, our DAP-FSR firstly employs its encoder to extract the multi-scale latent representations of the input LR face. Considering only one target domain example is available, we propose to augment the target domain data by mixing the latent representations of the target domain face and source domain ones, and then feed the mixed representations to the decoder of our DAP-FSR. The decoder will generate new face images resembling the target domain image style. The generated HR faces in turn are used to optimize our decoder to reduce the domain gap. By iteratively updating the latent representations and our decoder, our DAP-FSR will be adapted to the target domain, thus achieving authentic and high-quality upsampled HR faces. Extensive experiments on three newly constructed benchmarks validate the effectiveness and superior performance of our DAP-FSR compared to the state-of-the-art.