Research map / Detection and segmentation / Open-set and few-shot detection
Modelling and unsupervised learning of symmetric deformable object categories
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| train with symmetry-equivariance constraint (reflection in embedding space) instead of plain object frame | dense equivariant object frame model · CelebA eye symmetric landmark transfer | pixel error: 23.29 -> 3.21 | Helped |
| train with symmetry-equivariance constraint instead of baseline plus ad-hoc symmetry plane estimated from annotations | dense equivariant object frame model · CelebA eye symmetric landmark transfer | pixel error: 5.17 -> 3.21 | Helped |
| train with symmetry-equivariance constraint instead of baseline plus estimated plane | dense equivariant object frame model · CelebA mouth symmetric landmark transfer | pixel error: 5.38 -> 3.47 | Helped |
| add symmetry modelling to the object frame | dense equivariant object frame model · landmark matching across 200 face pairs | pixel error: 2.59 -> 2.60 | No clear effect |
| relax loss with minimum over symmetry group elements (rotational ambiguity) (ablation) | symmetric object frame · synthetic Clathrin protein with 3-fold rotational symmetry | alignment of object frame (qualitative) | Helped |
| scale synthetic warp intensity of training transformations (ablation) | symmetric object frame · CelebA symmetry error (eyes, mouth) | symmetry error (px) | Mixed |
Closest papers by meaning
- Unsupervised Learning of Probably Symmetric Deformable 3D Objects From Images in the Wild (CVPR 2020 · similarity 0.93)
- Unsupervised Part-Based Disentangling of Object Shape and Appearance (CVPR 2019 · similarity 0.87)
- Canonical 3D Deformer Maps: Unifying parametric and non-parametric methods for dense weakly-supervised category reconstruction (NeurIPS 2020 · similarity 0.87)
- RECON: Robust symmetry discovery via Explicit Canonical Orientation Normalization (ICLR 2026 · similarity 0.87)
- Learning Infinitesimal Generators of Continuous Symmetries from Data (NeurIPS 2024 · similarity 0.87)
- Symmetry Strikes Back: From Single-Image Symmetry Detection to 3D Generation (CVPR 2025 · similarity 0.86)
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.