# Towards Unbiased Label Distribution Learning for Facial Pose Estimation Using Anisotropic Spherical Gaussian

arXiv: https://arxiv.org/abs/2208.09122 · HTML: https://mlsanity.com/paper/2208.09122/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 52 references that are in the map.
- First posted on arXiv 19 Aug 2022.

## Builds on (most cited first, 24 of 24)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [On the Continuity of Rotation Representations in Neural Networks](https://mlsanity.com/paper/1812.07035/) (2018)
- [Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks](https://mlsanity.com/paper/1604.02878/) (2016)
- [PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes](https://mlsanity.com/paper/1711.00199/) (2017)
- [PVNet: Pixel-wise Voting Network for 6DoF Pose Estimation](https://mlsanity.com/paper/1812.11788/) (2018)
- [WIDER FACE: A Face Detection Benchmark](https://mlsanity.com/paper/1511.06523/) (2015)
- [DPOD: 6D Pose Object Detector and Refiner](https://mlsanity.com/paper/1902.11020/) (2019)
- [Fine-Grained Head Pose Estimation Without Keypoints](https://mlsanity.com/paper/1710.00925/) (2017)
- [HybridPose: 6D Object Pose Estimation under Hybrid Representations](https://mlsanity.com/paper/2001.01869/) (2020)
- [SG-Net: Spatial Granularity Network for One-Stage Video Instance Segmentation](https://mlsanity.com/paper/2103.10284/) (2021)
- [img2pose: Face Alignment and Detection via 6DoF, Face Pose Estimation](https://mlsanity.com/paper/2012.07791/) (2020)
- [Physical Attack on Monocular Depth Estimation with Optimal Adversarial Patches](https://mlsanity.com/paper/2207.04718/) (2022)
- [TF-Blender: Temporal Feature Blender for Video Object Detection](https://mlsanity.com/paper/2108.05821/) (2021)
- [A Vector-based Representation to Enhance Head Pose Estimation](https://mlsanity.com/paper/2010.07184/) (2020)
- [DenserNet: Weakly Supervised Visual Localization Using Multi-scale Feature Aggregation](https://mlsanity.com/paper/2012.02366/) (2020)
- [Multi-task head pose estimation in-the-wild](https://mlsanity.com/paper/2202.02299/) (2022)
- [FacePoseNet: Making a Case for Landmark-Free Face Alignment](https://mlsanity.com/paper/1708.07517/) (2017)
- [GL-RG: Global-Local Representation Granularity for Video Captioning](https://mlsanity.com/paper/2205.10706/) (2022)
- [Label distribution based facial attractiveness computation by deep residual learning](https://mlsanity.com/paper/1609.00496/) (2016)
- [Facial Pose Estimation by Deep Learning from Label Distributions](https://mlsanity.com/paper/1904.13102/) (2019)
- [Occlusion Resistant Object Rotation Regression from Point Cloud Segments](https://mlsanity.com/paper/1808.05498/) (2018)
- [Face Alignment Assisted by Head Pose Estimation](https://mlsanity.com/paper/1507.03148/) (2015)
- [A Realistic Face-to-Face Conversation System based on Deep Neural Networks](https://mlsanity.com/paper/1908.07750/) (2019)
- [Video synthesis of human upper body with realistic face](https://mlsanity.com/paper/1908.06607/) (2019)

## Built on by (most cited first, 7 of 7)

- [Visual Recognition with Deep Nearest Centroids](https://mlsanity.com/paper/2209.07383/) (2022)
- [TransFlow: Transformer as Flow Learner](https://mlsanity.com/paper/2304.11523/) (2023)
- [CML-MOTS: Collaborative Multi-task Learning for Multi-Object Tracking and Segmentation](https://mlsanity.com/paper/2311.00987/) (2023)
- [Label Distribution Learning via Implicit Distribution Representation](https://mlsanity.com/paper/2209.13824/) (2022)
- [Bidirectional Regression for Monocular 6DoF Head Pose Estimation and Reference System Alignment](https://mlsanity.com/paper/2407.14136/) (2024)
- [Adept: Annotation-Denoising Auxiliary Tasks with Discrete Cosine Transform Map and Keypoint for Human-Centric Pretraining](https://mlsanity.com/paper/2504.20800/) (2025)
- [VGGT-HPE: Reframing Head Pose Estimation as Relative Pose Prediction](https://mlsanity.com/paper/2604.10106/) (2026)

## Abstract (arXiv)

Facial pose estimation refers to the task of predicting face orientation from a single RGB image. It is an important research topic with a wide range of applications in computer vision. Label distribution learning (LDL) based methods have been recently proposed for facial pose estimation, which achieve promising results. However, there are two major issues in existing LDL methods. First, the expectations of label distributions are biased, leading to a biased pose estimation. Second, fixed distribution parameters are applied for all learning samples, severely limiting the model capability. In this paper, we propose an Anisotropic Spherical Gaussian (ASG)-based LDL approach for facial pose estimation. In particular, our approach adopts the spherical Gaussian distribution on a unit sphere which constantly generates unbiased expectation. Meanwhile, we introduce a new loss function that allows the network to learn the distribution parameter for each learning sample flexibly. Extensive experimental results show that our method sets new state-of-the-art records on AFLW2000 and BIWI datasets.