AFLW2000-3D

Introduced by Zhu et al. in Face Alignment Across Large Poses: A 3D Solution

AFLW2000-3D is a dataset of 2000 images that have been annotated with image-level 68-point 3D facial landmarks. This dataset is used for evaluation of 3D facial landmark detection models. The head poses are very diverse and often hard to be detected by a CNN-based face detector.

Source: https://www.tensorflow.org/datasets/catalog/aflw2k3d

Homepage

Benchmarks

Add a new result Link an existing benchmark

Task	Dataset Variant	Best Model
Head Pose Estimation	AFLW2000	SRHP-Euler
Face Alignment	AFLW2000-3D	MNN+OR
3D Face Reconstruction	AFLW2000-3D	SADRNet
Face Alignment	AFLW2000	MNN+ORB
Face Swapping	AFLW2000-3D	FaceDancer
Facial Landmark Detection	AFLW2000-3D	JVCR
3D Face Alignment	AFLW2000-3D	SADRNet
3D Facial Landmark Localization	AFLW2000-3D	JVCR