← Назад к исследованиям

Исследования и Публикации

RetinaFace

Single-stage Dense Face Localisation in the Wild

RetinaFace combines accurate face detection with reliable five-point landmark localisation, making it a practical front-end for recognition and alignment-heavy pipelines.

Сведения о статье

RetinaFace: Single-stage Dense Face Localisation in the Wild

Публикация

CVPR 2020

Авторы

Jiankang Deng, Jia Guo, Yuxiang Zhou, Jinke Yu, Irene Kotsia, Stefanos Zafeiriou

Открыть статью

Обзор исследования

RetinaFace focuses on detecting difficult faces in real scenes while also returning landmarks that improve alignment quality. That combination makes it useful not only for detection benchmarks, but also for enterprise systems where downstream recognition accuracy depends on consistent cropping and pose normalization.

Сценарии применения

  • Face detection and alignment before recognition
  • Real-time video analytics and entry gate cameras
  • Image ingestion, cropping, and portrait normalization
  • Mobile capture flows that require stable landmark estimation

Ключевые преимущества

Jointly predicts face boxes and five facial landmarks in a single-stage detector, reducing pipeline complexity.

Dense supervision and context-aware design improve robustness on small, occluded, blurred, and profile faces.

Provides dependable alignment signals for recognition, quality assessment, and video analytics workflows.

Коммерческий контакт

Давайте обсудим ваши бизнес-задачи

Свяжитесь с InsightFace по вопросам лицензирования моделей, поддержки корпоративного внедрения, кастомной разработки ИИ или стратегического партнёрства.

Мы принимаем запросы только с корпоративных адресов электронной почты.