Research map / Point clouds / Shape and surface completion
kh: Symmetry Understanding of 3D Shapes via Chirality Disentanglement
Weikang Wang, Tobias Weißberg, Nafie El Amrani, Florian Bernard
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| add chirality feature to Diff3F | Diff3F · SHREC'19 matching | matching error: 1.69 -> 1.02 | Improved |
| add chirality feature to Diff3F | Diff3F · TOSCA-a matching | matching error: 5.44 -> 4.72 | Improved |
| add chirality feature to Diff3F | Diff3F · TOSCA-a matching | matching accuracy: 20.25 -> 22.73 | Improved |
| add L_dis dissimilarity loss (ablation) | chirality extractor · FAUST | chirality accuracy: 51.34 -> 95.79 | Improved |
| add L_var total variation loss (ablation) | chirality extractor · FAUST | chirality accuracy: 77.02 -> 95.79 | Improved |
| add L_var total variation loss (ablation) | chirality extractor · SMAL | chirality accuracy: 74.37 -> 94.71 | Improved |
| add L_fif fifty-fifty loss (ablation) | chirality extractor · FAUST | chirality accuracy: 96.26 -> 95.79 | Hurt |
| add L_inv invertibility loss (ablation) | chirality extractor · SMAL | chirality accuracy: 76.72 -> 94.71 | Improved |
| add L_fif fifty-fifty loss (ablation) | chirality extractor · SMAL | chirality accuracy: 96.41 -> 94.71 | Hurt |
| add SD features to DINO (ablation) | chirality extractor · SMAL | chirality accuracy: 71.65 -> 94.71 | Improved |
| add DINO features to SD (ablation) | chirality extractor · FAUST | chirality accuracy: 81.47 -> 95.79 | Improved |
| normalise chirality feature by whole vector instead of tanh (ablation) | chirality extractor · BeCoS | chirality accuracy: 75.46 -> 91.84 | Improved |
Closest papers by meaning
- Learning to Detect 3D Symmetry From Single-View RGB-D Images With Weak Supervision (TPAMI 2022 · similarity 0.85)
- Unsupervised Pixel-Level Semantic Left-Right Understanding of In-the-Wild Images (ECCV 2026 · similarity 0.85)
- Symmetry Strikes Back: From Single-Image Symmetry Detection to 3D Generation (CVPR 2025 · similarity 0.83)
- HOPE: Shape Matching Via Aligning Different K-hop Neighbourhoods (NeurIPS 2024 · similarity 0.83)
- Leveraging 3D Geometric Priors in 2D Rotation Symmetry Detection (CVPR 2025 · similarity 0.82)
- Symmetry-Robust 3D Orientation Estimation (ICML 2025 · similarity 0.82)
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.
