Research map / 3D vision / Face and shape
Learning Continuous Implicit Representation for Near-Periodic Patterns
Bowei Chen, Tiancheng Zhi, Martial Hebert, Srinivasa G. Narasimhan
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 periodicity-aware input warping and periodicity prior (ablation) | NPP-Net · NRTDB | LPIPS: 0.429 -> 0.188 | Improved |
| add periodicity-aware input warping and periodicity prior (ablation) | NPP-Net · DTD | LPIPS: 0.468 -> 0.249 | Improved |
| add periodicity-guided patch loss to pixel loss (pixel only to full) (ablation) | NPP-Net · NRTDB | LPIPS: 0.308 -> 0.188 | Improved |
| add pixel loss to patch loss (patch only to full) (ablation) | NPP-Net · NRTDB | LPIPS: 0.322 -> 0.188 | Improved |
| sample patches by periodicity instead of randomly (ablation) | NPP-Net · NRTDB | LPIPS: 0.216 -> 0.188 | Improved |
| sample patches by periodicity instead of randomly (ablation) | NPP-Net · Facade | LPIPS: 0.316 -> 0.263 | Improved |
| add periodicity proposal with Top-3 candidates and offsets to initial pipeline (ablation) | NPP-Net · NRTDB | LPIPS: 0.213 -> 0.188 | Improved |
| use Top-3 instead of Top-1 periodicities (with offsets) (ablation) | NPP-Net · NRTDB | LPIPS: 0.205 -> 0.188 | Improved |
| use Top-3 instead of Top-5 periodicities (with offsets) (ablation) | NPP-Net · NRTDB | LPIPS: 0.197 -> 0.188 | Improved |
| add fine-level offsets to Top-3 periodicities (ablation) | NPP-Net · NRTDB | LPIPS: 0.210 -> 0.188 | Improved |
| NPP-Net versus Lama on non-strictly periodic facades | NPP-Net · Facade | LPIPS: 0.207 vs 0.263 | Hurt |
| NPP-Net versus Lama trained on large datasets | NPP-Net · NRTDB | LPIPS: 0.196 -> 0.188 | Improved |
Closest papers by meaning
- Topological Periodicity Test (TopPT) via Confidence Bound of Time-Delay Embeddings (NeurIPS 2026 · similarity 0.82)
- Neural Functions for Learning Periodic Signal (ICLR 2025 · similarity 0.82)
- Spot the Error: Non-autoregressive Graphic Layout Generation with Wireframe Locator (AAAI 2024 · similarity 0.82)
- Pattern Analogies: Learning to Perform Programmatic Image Edits by Analogy (CVPR 2025 · similarity 0.82)
- FINER: Flexible Spectral-bias Tuning in Implicit NEural Representation by Variable-periodic Activation Functions (CVPR 2024 · similarity 0.82)
- Implicit Representations for Constrained Image Segmentation (ICML 2024 · similarity 0.81)
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.
