# CLERF: Contrastive LEaRning for Full Range Head Pose Estimation

arXiv: https://arxiv.org/abs/2412.02066 · HTML: https://mlsanity.com/paper/2412.02066/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 41 references that are in the map.
- First posted on arXiv 3 Dec 2024.

## Builds on (most cited first, 21 of 21)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)
- [Circle Loss: A Unified Perspective of Pair Similarity Optimization](https://mlsanity.com/paper/2002.10857/) (2020)
- [Towards Fast, Accurate and Stable 3D Dense Face Alignment](https://mlsanity.com/paper/2009.09960/) (2020)
- [Panoptic Studio: A Massively Multiview System for Social Interaction Capture](https://mlsanity.com/paper/1612.03153/) (2016)
- [Fine-Grained Head Pose Estimation Without Keypoints](https://mlsanity.com/paper/1710.00925/) (2017)
- [Face Alignment in Full Pose Range: A 3D Total Solution](https://mlsanity.com/paper/1804.01005/) (2018)
- [PanoHead: Geometry-Aware 3D Full-Head Synthesis in 360circ](https://mlsanity.com/paper/2303.13071/) (2023)
- [WHENet: Real-time Fine-Grained Estimation for Wide Range Head Pose](https://mlsanity.com/paper/2005.10353/) (2020)
- [A Vector-based Representation to Enhance Head Pose Estimation](https://mlsanity.com/paper/2010.07184/) (2020)
- [Towards Robust and Unconstrained Full Range of Rotation Head Pose Estimation](https://mlsanity.com/paper/2309.07654/) (2023)
- [Pose-disentangled Contrastive Learning for Self-supervised Facial Representation](https://mlsanity.com/paper/2211.13490/) (2022)
- [Contrastive Representation Learning for Gaze Estimation](https://mlsanity.com/paper/2210.13404/) (2022)
- [On the representation and methodology for wide and short range head pose estimation](https://mlsanity.com/paper/2401.05807/) (2024)
- [RankPose: Learning Generalised Feature with Rank Supervision for Head Pose Estimation](https://mlsanity.com/paper/2005.10984/) (2020)
- [Temporal Representation Learning on Monocular Videos for 3D Human Pose Estimation](https://mlsanity.com/paper/2012.01511/) (2020)
- [LwPosr: Lightweight Efficient Fine-Grained Head Pose Estimation](https://mlsanity.com/paper/2202.03544/) (2022)
- [Mathematical Foundation and Corrections for Full Range Head Pose Estimation](https://mlsanity.com/paper/2403.18104/) (2024)
- [Semi-Supervised Unconstrained Head Pose Estimation in the Wild](https://mlsanity.com/paper/2404.02544/) (2024)

## Abstract (arXiv)

We introduce a novel framework for representation learning in head pose estimation (HPE). Previously such a scheme was difficult due to head pose data sparsity, making triplet sampling infeasible. Recent progress in 3D generative adversarial networks (3D-aware GAN) has opened the door for easily sampling triplets (anchor, positive, negative). We perform contrastive learning on extensively augmented data including geometric transformations and demonstrate that contrastive learning allows networks to learn genuine features that contribute to accurate HPE. On the other hand, we observe that existing HPE works struggle to predict head poses as accurately when test image rotation matrices are slightly out of the training dataset distribution. Experiments show that our methodology performs on par with state-of-the-art models on standard test datasets and outperforms them when images are slightly rotated/ flipped or full range head pose. To the best of our knowledge, we are the first to deliver a true full range HPE model capable of accurately predicting any head pose including upside-down pose. Furthermore, we compared with other existing full-yaw range models and demonstrated superior results.