← Voltar para Pesquisa

Pesquisa e Publicações

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.

Detalhes do artigo

RetinaFace: Single-stage Dense Face Localisation in the Wild

Publicação

CVPR 2020

Autores

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

Abrir artigo

Visão geral da pesquisa

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.

Aplicações em produção

  • 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

Principais contribuições

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.

Contato comercial

Vamos conversar sobre as suas necessidades de negócio

Fale com a InsightFace sobre licenciamento de modelos, suporte de implantação empresarial, desenvolvimento de IA sob medida ou parcerias estratégicas.

Aceitamos apenas consultas de endereços de e-mail corporativos.