# Fine-Grained Head Pose Estimation Without Keypoints

arXiv: https://arxiv.org/abs/1710.00925 · HTML: https://mlsanity.com/paper/1710.00925/

## Key facts

- Cited by 163 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Oct 2017.

## Built on by (most cited first, 30 of 163)

- [SadTalker: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation](https://mlsanity.com/paper/2211.12194/) (2022)
- [SimSwap: An Efficient Framework For High Fidelity Face Swapping](https://mlsanity.com/paper/2106.06340/) (2021)
- [HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editing](https://mlsanity.com/paper/2111.15666/) (2021)
- [One Shot Face Swapping on Megapixels](https://mlsanity.com/paper/2105.04932/) (2021)
- [GAN-Control: Explicitly Controllable GANs](https://mlsanity.com/paper/2101.02477/) (2021)
- [DiffFace: Diffusion-based Face Swapping with Facial Guidance](https://mlsanity.com/paper/2212.13344/) (2022)
- [Fine-Grained Face Swapping via Regional GAN Inversion](https://mlsanity.com/paper/2211.14068/) (2022)
- [Deepfake Generation and Detection: A Benchmark and Survey](https://mlsanity.com/paper/2403.17881/) (2024)
- [6D Rotation Representation For Unconstrained Head Pose Estimation](https://mlsanity.com/paper/2202.12555/) (2022)
- [Discovering Interpretable Directions in the Semantic Latent Space of Diffusion Models](https://mlsanity.com/paper/2303.11073/) (2023)
- [Learning Probabilistic Ordinal Embeddings for Uncertainty-Aware Regression](https://mlsanity.com/paper/2103.13629/) (2021)
- [High-resolution Face Swapping via Latent Semantics Disentanglement](https://mlsanity.com/paper/2203.15958/) (2022)
- [Third Time's the Charm? Image and Video Editing with StyleGAN3](https://mlsanity.com/paper/2201.13433/) (2022)
- [Region-Aware Face Swapping](https://mlsanity.com/paper/2203.04564/) (2022)
- [OrdinalCLIP: Learning Rank Prompts for Language-Guided Ordinal Regression](https://mlsanity.com/paper/2206.02338/) (2022)
- [FaceDancer: Pose- and Occlusion-Aware High Fidelity Face Swapping](https://mlsanity.com/paper/2210.10473/) (2022)
- [MobileFaceSwap: A Lightweight Framework for Video Face Swapping](https://mlsanity.com/paper/2201.03808/) (2022)
- [StyleSwap: Style-Based Generator Empowers Robust Face Swapping](https://mlsanity.com/paper/2209.13514/) (2022)
- [FaceXFormer: A Unified Transformer for Facial Analysis](https://mlsanity.com/paper/2403.12960/) (2024)
- [FSGANv2: Improved Subject Agnostic Face Swapping and Reenactment](https://mlsanity.com/paper/2202.12972/) (2022)
- [DAD-3DHeads: A Large-scale Dense, Accurate and Diverse Dataset for 3D Head Alignment from a Single Image](https://mlsanity.com/paper/2204.03688/) (2022)
- [Multimodal Engagement Analysis from Facial Videos in the Classroom](https://mlsanity.com/paper/2101.04215/) (2021)
- [Synergy between 3DMM and 3D Landmarks for Accurate 3D Facial Geometry](https://mlsanity.com/paper/2110.09772/) (2021)
- [MOST-GAN: 3D Morphable StyleGAN for Disentangled Face Image Manipulation](https://mlsanity.com/paper/2111.01048/) (2021)
- [3D-aware Conditional Image Synthesis](https://mlsanity.com/paper/2302.08509/) (2023)
- [FaceXBench: Evaluating Multimodal LLMs on Face Understanding](https://mlsanity.com/paper/2501.10360/) (2025)
- [Multi-task head pose estimation in-the-wild](https://mlsanity.com/paper/2202.02299/) (2022)
- [Unimodal-Concentrated Loss: Fully Adaptive Label Distribution Learning for Ordinal Regression](https://mlsanity.com/paper/2204.00309/) (2022)
- [CustomListener: Text-guided Responsive Interaction for User-friendly Listening Head Generation](https://mlsanity.com/paper/2403.00274/) (2024)
- [Faces that Speak: Jointly Synthesising Talking Face and Speech from Text](https://mlsanity.com/paper/2405.10272/) (2024)

## Abstract (arXiv)

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. Traditionally head pose is computed by estimating some keypoints from the target face and solving the 2D to 3D correspondence problem with a mean human head model. We argue that this is a fragile method because it relies entirely on landmark detection performance, the extraneous head model and an ad-hoc fitting step. We present an elegant and robust way to determine pose by training a multi-loss convolutional neural network on 300W-LP, a large synthetically expanded dataset, to predict intrinsic Euler angles (yaw, pitch and roll) directly from image intensities through joint binned pose classification and regression. We present empirical tests on common in-the-wild pose benchmark datasets which show state-of-the-art results. Additionally we test our method on a dataset usually used for pose estimation using depth and start to close the gap with state-of-the-art depth pose methods. We open-source our training and testing code as well as release our pre-trained models.