mlsanityData to 7 Oct 2026

6D Rotation Representation For Unconstrained Head Pose Estimation

arXiv 2202.12555 ↗First posted 25 Feb 2022cs.CV cs.AI cs.LGcited by 63

Not on the map. Why?

Abstract (arXiv)

In this paper, we present a method for unconstrained end-to-end head pose estimation. We address the problem of ambiguous rotation labels by introducing the rotation matrix formalism for our ground truth data and propose a continuous 6D rotation matrix representation for efficient and robust direct regression. This way, our method can learn the full rotation appearance which is contrary to previous approaches that restrict the pose prediction to a narrow-angle for satisfactory results. In addition, we propose a geodesic distance-based loss to penalize our network with respect to the SO(3) manifold geometry. Experiments on the public AFLW2000 and BIWI datasets demonstrate that our proposed method significantly outperforms other state-of-the-art methods by up to 20%. We open-source our training and testing code along with our pre-trained models: https://github.com/thohemp/6DRepNet.

Key facts. Cited by 63 papers in the map (data through 7 Oct 2026). Builds on 9 of its 20 references that are in the map. First posted on arXiv 25 Feb 2022.

Builds on

9 of 20 references.

References · 9

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Going Deeper with Convolutionscited by 4,231
  3. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,186
  4. 2016Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networkscited by 895
  5. 2021RepVGG: Making VGG-style ConvNets Great Againcited by 520
  6. 2017Fine-Grained Head Pose Estimation Without Keypointscited by 163
  7. 2018Face Alignment in Full Pose Range: A 3D Total Solutioncited by 147
  8. 2020WHENet: Real-time Fine-Grained Estimation for Wide Range Head Posecited by 47
  9. 2020A Vector-based Representation to Enhance Head Pose Estimationcited by 34

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 5; 2023: 13; 2024: 26; 2025: 4; 2026: 15.

63 papers.

Sort:

By area:

  1. 2024Shape of Motion: 4D Reconstruction from a Single Videocited by 247
  2. 2024FaceXFormer: A Unified Transformer for Facial Analysiscited by 34
  3. 2022DATID-3D: Diversity-Preserved Domain Adaptation Using Text-to-Image Diffusion for 3D Generative Modelcited by 32
  4. 2022Synthetic Data in Human Analysis: A Surveycited by 28
  5. 2024EgoLM: Multi-Modal Language Model of Egocentric Motionscited by 28
  6. 2025FaceXBench: Evaluating Multimodal LLMs on Face Understandingcited by 23
  7. 2023Towards Robust and Unconstrained Full Range of Rotation Head Pose Estimationcited by 20
  8. 2023Unsupervised Volumetric Animationcited by 18
  9. 2024On the representation and methodology for wide and short range head pose estimationcited by 11
  10. 2024CloudFixer: Test-Time Adaptation for 3D Point Clouds via Diffusion-Guided Geometric Transformationcited by 11
  11. 2026Wall-OSS-0.5 Technical Reportcited by 11
  12. 2023Disguise without Disruption: Utility-Preserving Face De-Identificationcited by 8
38 more
  1. 2025SENTINEL: A Fully End-to-End Language-Action Model for Humanoid Whole Body Controlcited by 7
  2. 2023DirectMHP: Direct 2D Multi-Person Head Pose Estimation with Full-range Anglescited by 6
  3. 2023DSFNet: Dual Space Fusion Network for Occlusion-Robust 3D Dense Face Alignmentcited by 6
  4. 2024Two-in-One: Unified Multi-Person Interactive Motion Generation by Latent Diffusion Transformercited by 6
  5. 2026X-Tokenizer: A Multimodal Action Tokenizer for Vision-Language-Action Pretrainingcited by 6
  6. 2022GOTCHA: Real-Time Video Deepfake Detection via Challenge-Responsecited by 5
  7. 2024Edit One for All: Interactive Batch Image Editingcited by 5
  8. 2024Task-adaptive Q-Facecited by 5
  9. 2024Geometric Transformation Uncertainty for Improving 3D Fetal Brain Pose Prediction from Freehand 2D Ultrasound Videoscited by 5
  10. 2023Robust Self-Supervised Extrinsic Self-Calibrationcited by 4
  11. 20232D Image head pose estimation via latent space regression under occlusion settingscited by 3
  12. 2024Mathematical Foundation and Corrections for Full Range Head Pose Estimationcited by 3
  13. 2024Skip-and-Play: Depth-Driven Pose-Preserved Image Generation for Any Objectscited by 3
  14. 2022An Intuitive and Unconstrained 2D Cube Representation for Simultaneous Head Detection and Pose Estimationcited by 2
  15. 2023Pose Impact Estimation on Face Recognition using 3D-Aware Synthetic Data with Application to Quality Assessmentcited by 2
  16. 2024Semi-Supervised Unconstrained Head Pose Estimation in the Wildcited by 2
  17. 2024FaceLift: Semi-supervised 3D Facial Landmark Localizationcited by 2
  18. 2024ReMP: Reusable Motion Prior for Multi-domain 3D Human Pose Estimation and Motion Inbetweeningcited by 2
  19. 2024Fairer Analysis and Demographically Balanced Face Generation for Fairer Face Verificationcited by 2
  20. 2022Extreme-scale Talking-Face Video Upsampling with Audio-Visual Priorscited by 1
  21. 2023Appearance-based gaze estimation enhanced with synthetic images using deep neural networkscited by 1
  22. 2024Alignment Helps Make the Most of Multimodal Datacited by 1
  23. 2024Rank-based No-reference Quality Assessment for Face Swappingcited by 1
  24. 2024HPE-CogVLM: Advancing Vision Language Models with a Head Pose Grounding Taskcited by 1
  25. 2024For a semiotic AI: Bridging computer vision and visual semiotics for computational observation of large scale facial image archivescited by 1
  26. 2024Full-range Head Pose Geometric Data Augmentationscited by 1
  27. 2024ORFormer: Occlusion-Robust Transformer for Accurate Facial Landmark Detectioncited by 1
  28. 2025StyleMorpheus: A Style-Based 3D-Aware Morphable Face Modelcited by 1
  29. 2026Beyond Coherence: Benchmarking Professional Editing-Technique Execution in Multi-Shot Audio-Video Generationcited by 1
  30. 2023Sentiment-based Engagement Strategies for intuitive Human-Robot Interactioncited by 0
  31. 20233D Face Alignment Through Fusion of Head Pose Information and Featurescited by 0
  32. 2023NITEC: Versatile Hand-Annotated Eye Contact Dataset for Ego-Vision Interactioncited by 0
  33. 2023VerA: Versatile Anonymization Applicable to Clinical Facial Photographscited by 0
  34. 2024Latent Embedding Clustering for Occlusion Robust Head Pose Estimationcited by 0
  35. 2024Toward Fairer Face Recognition Datasetscited by 0
  36. 2024On the power of data augmentation for head pose estimationcited by 0
  37. 2024Bidirectional Regression for Monocular 6DoF Head Pose Estimation and Reference System Alignmentcited by 0
  38. 2024End to End Face Reconstruction via Differentiable PnPcited by 0

50 most cited of 63 All 63 (JSON)