PK PyTorchKR Papers
Papers with Code · CC BY-SA 4.0

Face Alignment

Face Reconstruction › 3D Face Reconstruction › Facial Recognition and Modelling › Face Alignment 213 평가 기록 26 datasets

Face alignment is the task of identifying the geometric structure of faces in digital images, and attempting to obtain a canonical alignment of the face based on translation, scale, and rotation.

<span style="color:grey; opacity: 0.6">( Image credit: 3DDFA_V2 )</span>

개요는 각 항목의 일부입니다. 위 탭에서 전체 기록을 페이지별로 탐색할 수 있습니다.

벤치마크

Papers with Code 아카이브의 데이터셋별 기록 예시입니다. 평가 조건과 지표 방향이 검증되지 않아 순위를 의미하지 않습니다.

Dataset기록된 모델 예시MetricPaperCode
STAR
NME_inter-ocular (%, Full): 2.87NME_inter-ocular (%, Common): 2.52NME_inter-ocular (%, Challenge): 4.32NME_inter-pupil (%, Full): 4.03
논문 코드
SH-FAN
NME (inter-ocular): 3.72AUC@10 (inter-ocular): 63.81FR@10 (inter-ocular): 1.55
논문 -
FiFA
NME (inter-ocular): 2.96
논문 -
FiFA
NME_diag (%, Full): 0.92NME_diag (%, Frontal): 0.80NME_box (%, Full): 1.31AUC_box@0.07 (%, Full): 81.8
논문 -
MNN+OR (reannotated)
Balanced NME (2D Sparse Alignment): 2.58%
논문 코드
SH-FAN
NME (inter-ocular): 3.72AUC@10 (inter-ocular): 63.1FR@10 (inter-ocular): 1.55
논문 -
SPIGA
NME (box): 2.03AUC@7 (box): 71.0NME (inter-ocular): 3.43AUC@8 (inter-ocular): 57.27
논문 코드
SPIGA
NME (box): 2.52AUC@7 (box): 64.1NME (inter-ocular): 3.93
논문 코드
MNN+ORB (Reannotated)
Error rate: 2.58
논문 코드
SH-FAN
NME (inter-ocular): 2.94NME (bbox): 2.04AUC@7 (bbox): 71.1
논문 -
SH-FAN
NME (box): 2.47AUC@7: 64.9
논문 -
ASM
NME: 0.21
논문 -

데이터셋

26개
300WWFLWCOFWAFLW-19AFLW2000-3DWFW (Extra Data)300W Split 2COFW-68AFLW2000300W Split 2 (300W-LP)COFW-68 (300WLP)FaceScape

논문

라이브러리

Papers with Code 리더보드 row에 연결된 구현 저장소입니다.

github.com/163GitHub/AI 1 논문
github.com/1adrianb/unsupervised-face-representation 1 논문
github.com/2023-MindSpore-1/ms-code-214/tree/main/HRNetW48_seg 1 논문
github.com/abhi1kumar/hrnet_pose_single_gpu 1 논문
github.com/anshky/HR-NET 1 논문
github.com/baoshengyu/deep-high-resolution-net.pytorch 1 논문
github.com/Burf/HRNetV2-OCR-Tensorflow2 1 논문
github.com/CSAILVision/semantic-segmentation-pytorch 1 논문