TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK	REMOVE
Head Pose Estimation	AFLW2000	DAD-3DNet	MAE	3.66	# 6
Head Pose Estimation	BIWI	DAD-3DNet	MAE (trained with BIWI data)	3.98	# 7

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/dad-3dheads-a-large-scale-dense-accurate-and/head-pose-estimation-on-aflw2000)](https://paperswithcode.com/sota/head-pose-estimation-on-aflw2000?p=dad-3dheads-a-large-scale-dense-accurate-and)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/dad-3dheads-a-large-scale-dense-accurate-and/head-pose-estimation-on-biwi)](https://paperswithcode.com/sota/head-pose-estimation-on-biwi?p=dad-3dheads-a-large-scale-dense-accurate-and)`

DAD-3DHeads: A Large-scale Dense, Accurate and Diverse Dataset for 3D Head Alignment from a Single Image

CVPR 2022 · Tetiana Martyniuk, Orest Kupyn, Yana Kurlyak, Igor Krashenyi, Jiři Matas, Viktoriia Sharmanska ·

We present DAD-3DHeads, a dense and diverse large-scale dataset, and a robust model for 3D Dense Head Alignment in the wild. It contains annotations of over 3.5K landmarks that accurately represent 3D head shape compared to the ground-truth scans. The data-driven model, DAD-3DNet, trained on our dataset, learns shape, expression, and pose parameters, and performs 3D reconstruction of a FLAME mesh. The model also incorporates a landmark prediction branch to take advantage of rich supervision and co-training of multiple related tasks. Experimentally, DAD-3DNet outperforms or is comparable to the state-of-the-art models in (i) 3D Head Pose Estimation on AFLW2000-3D and BIWI, (ii) 3D Face Shape Reconstruction on NoW and Feng, and (iii) 3D Dense Head Alignment and 3D Landmarks Estimation on DAD-3DHeads dataset. Finally, the diversity of DAD-3DHeads in camera angles, facial expressions, and occlusions enables a benchmark to study in-the-wild generalization and robustness to distribution shifts. The dataset webpage is https://p.farm/research/dad-3dheads.