← 연구로 돌아가기

연구 및 출판물

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.

논문 정보

RetinaFace: Single-stage Dense Face Localisation in the Wild

게재 정보

CVPR 2020

저자

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

논문 보기

연구 개요

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.

프로덕션 활용 사례

  • 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

핵심 기여

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.

비즈니스 문의

비즈니스 요구사항을 상담해 보세요

모델 라이선스, 엔터프라이즈 배포 지원, 맞춤형 AI 개발, 전략적 파트너십 관련 문의는 InsightFace로 연락해 주세요.

비즈니스 이메일 주소에서의 문의만 접수합니다.