Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

© 2026 Papersgraph. All rights reserved.

computer-vision-7

Head Pose Estimation

3260 papers • 126 benchmarks • 313 datasets

Estimating the head pose of a person is a crucial problem that has a large amount of applications such as aiding in gaze estimation, modeling attention, fitting 3D models to video and performing face alignment. ( Image credit: FSA-Net: Learning Fine-Grained Structure Aggregation for Head Pose Estimation from a Single Image )

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in head-pose-estimation-7

Trend

Dataset

Best Model

Actions

BIWI

BIWI

AFLW2000

AFLW2000

AFLW

AFLW

Libraries

i

Use these libraries to find head-pose-estimation-7 models and implementations

paplhjak/facial-age-estimation-benc…

2 papers 27

Datasets

AFLW

AFLW2000-3D

Panoptic

COFW

WFLW

BIWI

Subtasks

No subtasks available.

Most implemented papers

Fine-Grained Head Pose Estimation Without Keypoints

James M. Rehg, Eunji Chong, Nataniel Ruiz•Sun Oct 01 2017

An elegant and robust way to determine pose is presented by training a multi-loss convolutional neural network on 300W-LP, a large synthetically expanded dataset, to predict intrinsic Euler angles directly from image intensities through joint binned pose classification and regression.

590

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

Panoptic

Panoptic

WFLW

WFLW

Pointing'04

Pointing'04

BJUT-3D

BJUT-3D

COFW

COFW

CMU Panoptic + 300W-LP

CMU Panoptic + 300W-LP

BIWI

Biwi Kinect Head Pose

Biwi Kinect Head Pose

DAD-3DHeads

HPD

ICT-3DHP

0

How Far are We from Solving the 2D & 3D Face Alignment Problem? (and a Dataset of 230,000 3D Facial Landmarks)

Georgios Tzimiropoulos, Adrian Bulat•Mon Mar 20 2017

This paper investigates how far a very deep neural network is from attaining close to saturating performance on existing 2D and 3D face alignment datasets and builds a very strong baseline for this purpose.

1601 0

WHENet: Real-time Fine-Grained Estimation for Wide Range Head Pose

Yijun Zhou, J. Gregson•Tue May 19 2020

The resulting Wide Headpose Estimation Network (WHENet) is the first fine-grained modern method applicable to the full-range of head yaws yet also meets or beats state-of-the-art methods for frontal head pose estimation.

120 0

Synergy between 3DMM and 3D Landmarks for Accurate 3D Facial Geometry

Cho-Ying Wu, U. Neumann, Qiangeng Xu•Mon Oct 18 2021

This work studies learning from a synergy process of 3D Morphable Models (3DMM) and3D facial landmarks to predict complete 3D facial geometry, including 3D alignment, face orientation, and 3D face modeling.

75 0

Detect Faces Efficiently: A Survey and Evaluations

Shiqi Yu, Yuantao Feng, Hanyang Peng, Yan-Ran Li, Jianguo Zhang•Thu Dec 02 2021

A comprehensive comparison of several successful deep learning-based face detectors is conducted to uncover their efficiency using two metrics: FLOPs and latency and can guide to choose appropriate face detectors for different applications and also to develop more efficient and accurate detectors.

44 0

Deep Label Distribution Learning With Label Ambiguity

Jianxin Wu, Xin Geng, Bin-Bin Gao, Chao Xing, Chen-Wei Xie•Sat Nov 05 2016

The proposed deep label distribution learning (DLDL) method effectively utilizes the label ambiguity in both feature learning and classifier learning, which help prevent the network from overfitting even when the training set is small.

474 0

img2pose: Face Alignment and Detection via 6DoF, Face Pose Estimation

Guan Pang, Tal Hassner, Vítor Albiero, Xi Yin, Xingyu Chen•Sun Dec 13 2020

Tests show that the proposed real-time, six degrees of freedom, 3D face pose estimation without face detection or landmark localization outperforms state of the art (SotA) face pose estimators and surpasses SotA models of comparable complexity on the WIDER FACE detection benchmark, despite not been optimized on bounding box labels.

147 0

FaceXFormer: A Unified Transformer for Facial Analysis

R. Chellappa, VS Vibashan, Kartik Narayan, Vishal M. Patel•Mon Mar 18 2024

FaceXFormer is the first model capable of handling ten facial analysis tasks while maintaining real-time performance at 33.21 FPS, and FaceX, a lightweight decoder with a novel bi-directional cross-attention mechanism, which jointly processes face and task tokens to learn robust and generalized facial representations.

36 0

Face Alignment Assisted by Head Pose Estimation

H. Gunes, I. Patras, Wenxuan Mou, Heng Yang, Yichi Zhang, Peter Robinson•Tue Jun 30 2015

This paper proposes a supervised initialization scheme for cascaded face alignment based on explicit head pose estimation and proposes two schemes for generating initialisation: the first one relies on projecting a mean 3D face shape onto 2D image under the estimated head pose; the second one searches nearest neighbour shapes from the training set according to head pose distance.

76 0

A Multiresolution 3D Morphable Face Model and Fitting Framework

J. Kittler, Guosheng Hu, P. Huber, J. Tena, Pouria Mortazavian, W. P. Koppen, W. Christmas, Matthias Rätsch•Fri Feb 26 2016

The Surrey Face Model is presented, a multi-resolution 3D Morphable Model that is made available to the public for non-commercial purposes and a lightweight open-source C++ library designed with simplicity and ease of integration as its foremost goals.

239 0

Adding a benchmark result helps the community track progress.

Head Pose Estimation | State-of-the-Art