{"slug": "improving-low-resolution-face-recognition-under-limited-data-how-synthetic-data", "title": "Improving Low-Resolution Face Recognition under Limited Data: How Synthetic Data Generation Can Close the Domain Gap", "summary": "A study from Idiap Research Institute finds that simple interpolation-based degradation outperforms more complex generative methods for low-resolution face recognition on real-world data, exposing a synthetic-real gap. The researchers evaluated synthetic data generation strategies including Real-ESRGAN-style degradation and a learned super-resolution front-end on benchmarks LFW, CFP-FP, AgeDB-30, and TinyFace, concluding that generative methods must be validated on real LR data and against a direct-feed baseline.", "body_md": "arXiv:2608.06580v1 Announce Type: new\nAbstract: Face Recognition (FR) systems in surveillance settings often encounter Low Resolution (LR) faces, those whose face region falls below the standard 112 $\\times$ 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", "url": "https://wpnews.pro/news/improving-low-resolution-face-recognition-under-limited-data-how-synthetic-data", "canonical_source": "https://arxiv.org/abs/2608.06580", "published_at": "2026-08-10 04:00:00+00:00", "updated_at": "2026-08-10 04:14:28.754683+00:00", "lang": "en", "topics": ["computer-vision", "machine-learning", "generative-ai"], "entities": ["Idiap Research Institute", "LFW", "CFP-FP", "AgeDB-30", "TinyFace", "Real-ESRGAN"], "alternates": {"html": "https://wpnews.pro/news/improving-low-resolution-face-recognition-under-limited-data-how-synthetic-data", "markdown": "https://wpnews.pro/news/improving-low-resolution-face-recognition-under-limited-data-how-synthetic-data.md", "text": "https://wpnews.pro/news/improving-low-resolution-face-recognition-under-limited-data-how-synthetic-data.txt", "jsonld": "https://wpnews.pro/news/improving-low-resolution-face-recognition-under-limited-data-how-synthetic-data.jsonld"}}