Research map / 3D vision / Human pose estimation
HOGWARTS: Mitigating Perspective Distortion for 6DoF Head Pose Estimation via Virtual Camera Space
Sungho Chun, Ju Yong Chang
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes HOGWARTS, a 6DoF head pose estimation method that mitigates perspective distortion by working in a virtual camera space, addressing the geometric inconsistency of rectangular face cropping.
Problem
Estimating 6DoF head pose from a single RGB image is hard under strong perspective distortion; rectangular face cropping causes image-label mismatch under 2D rotation augmentation and worsens perspective ambiguity.
Approach
Reframes head pose estimation in a virtual camera space to remove the geometric inconsistency introduced by rectangular face cropping, so that projection distortion is no longer confused with head rotation.
Closest papers by meaning
- FAR: Flexible Accurate and Robust 6DoF Relative Camera Pose Estimation (CVPR 2024 · similarity 0.85)
- SingRef6D: Monocular Novel Object Pose Estimation with a Single RGB Reference (NeurIPS 2025 · similarity 0.84)
- iG-6DoF: Model-free 6DoF Pose Estimation for Unseen Object via Iterative 3D Gaussian Splatting (CVPR 2025 · similarity 0.84)
- RefPose: Leveraging Reference Geometric Correspondences for Accurate 6D Pose Estimation of Unseen Objects (CVPR 2025 · similarity 0.84)
- Any6D: Model-free 6D Pose Estimation of Novel Objects (CVPR 2025 · similarity 0.84)
- Relative Pose Estimation through Affine Corrections of Monocular Depth Priors (CVPR 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
