Research map / 3D vision / Human pose estimation
Distributional Estimation of 3D Object Orientation
Minjoon Kim, Chunghyun Park, Minsu Cho
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 distributional estimation of 3D object orientation to represent inherent canonical-orientation ambiguity from rotational symmetry rather than predicting a single output.
Problem
Canonical orientation of 3D objects is often not unique due to rotational symmetry, so single-output regressors cannot faithfully represent the set of valid orientations (an orbit of the symmetry group).
Approach
Model orientation as a distribution over valid canonical frames rather than a single pose, so that symmetric objects' multiple equally valid orientations are represented faithfully. Full method details unavailable from the abstract.
Closest papers by meaning
- Symmetry-Robust 3D Orientation Estimation (ICML 2025 · similarity 0.93)
- Leveraging 3D Geometric Priors in 2D Rotation Symmetry Detection (CVPR 2025 · similarity 0.89)
- Orient Anything V2: Unifying Orientation and Rotation Understanding (NeurIPS 2025 · similarity 0.88)
- Orientation Matters: Making 3D Generative Models Orientation-Aligned (NeurIPS 2025 · similarity 0.88)
- R2Det: Exploring Relaxed Rotation Equivariance in 2D Object Detection (ICLR 2025 · similarity 0.87)
- Orient Anything: Learning Robust Object Orientation Estimation from Rendering 3D Models (ICML 2025 · similarity 0.87)
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.
