# Improving Low-Resolution Face Recognition under Limited Data: How Synthetic Data Generation Can Close the Domain Gap

arXiv: https://arxiv.org/abs/2608.06580 · HTML: https://mlsanity.com/paper/2608.06580/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 32 references that are in the map.
- First posted on arXiv 6 Aug 2026.

## Builds on (most cited first, 17 of 17)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/1809.00219/) (2018)
- [Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network](https://mlsanity.com/paper/1609.05158/) (2016)
- [CosFace: Large Margin Cosine Loss for Deep Face Recognition](https://mlsanity.com/paper/1801.09414/) (2018)
- [Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data](https://mlsanity.com/paper/2107.10833/) (2021)
- [WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition](https://mlsanity.com/paper/2103.04098/) (2021)
- [Partial FC: Training 10 Million Identities on a Single Machine](https://mlsanity.com/paper/2010.05222/) (2020)
- [EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applications](https://mlsanity.com/paper/2206.10589/) (2022)
- [Low-Resolution Face Recognition](https://mlsanity.com/paper/1811.08965/) (2018)
- [EdgeFace: Efficient Face Recognition Model for Edge Devices](https://mlsanity.com/paper/2307.01838/) (2023)
- [Cross-Resolution Learning for Face Recognition](https://mlsanity.com/paper/1912.02851/) (2019)
- [Prepended Domain Transformer: Heterogeneous Face Recognition without Bells and Whistles](https://mlsanity.com/paper/2210.06529/) (2022)
- [FaceMe: Robust Blind Face Restoration with Personal Identification](https://mlsanity.com/paper/2501.05177/) (2025)
- [EFaR 2023: Efficient Face Recognition Competition](https://mlsanity.com/paper/2308.04168/) (2023)
- [Heterogeneous Face Recognition Using Domain Invariant Units](https://mlsanity.com/paper/2404.14343/) (2024)
- [Efficient Low-Resolution Face Recognition via Bridge Distillation](https://mlsanity.com/paper/2409.11786/) (2024)
- [Boosting Cross-Quality Face Verification using Blind Face Restoration](https://mlsanity.com/paper/2308.07967/) (2023)

## Abstract (arXiv)

Face Recognition (FR) systems in surveillance settings often encounter Low Resolution (LR) faces, those whose face region falls below the standard 112 × 112 input size. While labelled High Resolution (HR) training data is abundant, labelled native-LR data, and above all paired native LR/HR data, is scarce. One workaround is to synthesize LR data from the available HR faces, but how much synthesis effort is repaid in recognition accuracy remains unclear. We present a study of simple synthetic generation strategies for a compact, edge device-oriented face recognition system, spanning interpolation-based degradation, knowledge distillation, a Prepended Domain Transformer (PDT), Real ESRGAN-style degradation, and a learned Super Resolution (SR) front-end with an identity-aware loss. We evaluate these strategies on synthetic cross-resolution face benchmarks (LFW, CFP-FP, AgeDB-30) and on TinyFace, a real-world native LR dataset, and expose a synthetic-real gap: the degradation setting that is optimal on synthetic benchmarks is not the one that is optimal on real LR. We find that more synthesis effort does not help monotonically: the learned SR front-end does not surpass a direct feed of the aligned LR image into a strong backbone, while simple interpolation augmentation of a compact backbone is the only synthesis that improves over its own baseline. We conclude that generative methods for LR face recognition must be validated on real LR and against a direct-feed baseline, and release our pipeline at https://idiap.ch/paper/synth-lrfr