← Volver a Investigación

Investigación y Publicaciones

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.

Detalles del paper

RetinaFace: Single-stage Dense Face Localisation in the Wild

Publicación

CVPR 2020

Autores

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

Abrir paper

Resumen de la investigación

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.

Aplicaciones en producción

  • 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

Aportes clave

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.

Contacto comercial

Conversemos sobre sus necesidades comerciales

Contacte con InsightFace para licencias de modelos, soporte de despliegue empresarial, desarrollo de IA a medida o conversaciones sobre alianzas estratégicas.

Solo aceptamos consultas desde direcciones de correo electrónico empresariales.