Research map / 3D vision / Face and shape
Neural Feature Matching in Implicit 3D Representations
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 |
|---|---|---|---|
| add regularisation penalty on displacement norm to Gauss-Newton feature matching (ablation) | implicit feature matching · qualitative (planar regions) | point placement on planar regions | Helped |
| match with latent-code interpolation instead of direct source-to-target matching (ablation) | implicit feature matching · qualitative (chairs) | shape plausibility | Helped |
| combine layer 3 features with layer 6 features (weight 0.1) (ablation) | mesh deformation via feature matching · qualitative (chairs) | local geometry fit to target | Helped |
| use deeper layer features (layer 6) for matching instead of mid-layer (ablation) | implicit feature matching · chair edge preservation | preserved edge rate (%) | Hurt |
| feature matching (layer 3) instead of appearance-fitting for mesh deformation | mesh deformation · ShapeNetPart chair/airplane/table part-level | part-level CD and EMD | Mixed |
| nearest-neighbour correspondence from implicit features (no supervision) vs. without features | OccNet implicit features on D-FAUST · D-FAUST correspondence | Cor. l2 (lower better): 0.374 -> 0.169 | Helped |
Closest papers by meaning
- Implicit Functions in Feature Space for 3D Shape Reconstruction and Completion (CVPR 2020 · similarity 0.89)
- Local Deep Implicit Functions for 3D Shape (CVPR 2020 · similarity 0.88)
- Few-Shot Unsupervised Implicit Neural Shape Representation Learning with Spatial Adversaries (ICML 2024 · similarity 0.88)
- 4Deform: Neural Surface Deformation for Robust Shape Interpolation (CVPR 2025 · similarity 0.88)
- Implicit Modeling of Non-rigid Objects with Cross-Category Signals (AAAI 2024 · similarity 0.87)
- Implicit Neural Surface Deformation with Explicit Velocity Fields (ICLR 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.