Research map / 3D vision / Face and shape
PINs: Progressive Implicit Networks for Multi-Scale Neural 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 |
|---|---|---|---|
| use progressive Fourier-feature subsets in a hierarchical MLP | PINs · 3D Warehouse shapes | Chamfer Distance | Helped |
| use progressive Fourier-feature subsets in a hierarchical MLP | PINs · ImageNet test | MSE: 0.0030 $\pm$ 8.6$\mathrm{e}{-6}$ -> 0.0027$\pm$1.6$\mathrm{e}{-6}$ | Helped |
| use progressive Fourier-feature subsets in a hierarchical MLP | PINs · DIV2K validation | MSE: 2.0$\mathrm{e}{-3}\pm$2.2$\mathrm{e}{-6}$ -> 1.88$\mathrm{e}{-3}\pm$2.26$\mathrm{e}{-6}$ | Helped |
| remove level-conditioning from higher layers (ablation) | PINs · DIV2K validation | MSE: 1.88$\mathrm{e}{-3}\pm$2.26$\mathrm{e}{-6}$ -> 2.07$\mathrm{e}{-3}\pm$2.87$\mathrm{e}{-6}$ | Hurt |
| use decreasing weights rather than equal weights for level composition (ablation) | PINs · ImageNet test | MSE: 0.0028$\pm9.4$ $\mathrm{e}{-6}$ -> 0.0027$\pm$1.6$\mathrm{e}{-6}$ | Helped |
| use decreasing weights rather than equal weights for level composition (ablation) | PINs · ImageNet test | PSNR: 75.9$\pm$24.82 -> 75.9$\pm$23.49 | Hurt |
| use decreasing weights rather than equal weights for level composition (ablation) | PINs · DIV2K validation | MSE: 1.91$\mathrm{e}{-3}\pm$2.46$\mathrm{e}{-6}$ -> 1.88$\mathrm{e}{-3}\pm$2.26$\mathrm{e}{-6}$ | Helped |
| use decreasing weights rather than equal weights for level composition (ablation) | PINs · DIV2K validation | PSNR: 76.9$\pm$18.9 -> 76.8$\pm$13.6 | Hurt |
| vary the number of levels while holding parameter count fixed (ablation) | PINs · DIV2K validation | reconstruction accuracy | Mixed |
| vary the number of levels while holding parameter count fixed (ablation) | PINs · 3D Warehouse shapes | reconstruction accuracy | Mixed |
Closest papers by meaning
- CoordX: Accelerating Implicit Neural Representation with a Split MLP Architecture (ICLR 2022 · similarity 0.87)
- Optimizing Rank for High-Fidelity Implicit Neural Representations (ICML 2026 · similarity 0.86)
- PM-INR: Prior-Rich Multi-Modal Implicit Large-Scale Scene Neural Representation (AAAI 2024 · similarity 0.85)
- Adaptive Wavelet-Positional Encoding for High-Frequency Information Learning in Implicit Neural Representation (AAAI 2025 · similarity 0.85)
- Implicit Zoo: A Large-Scale Dataset of Neural Implicit Functions for 2D Images and 3D Scenes (NeurIPS 2024 · similarity 0.84)
- Synergistic Integration of Coordinate Network and Tensorial Feature for Improving Neural Radiance Fields from Sparse Inputs (ICML 2024 · similarity 0.84)
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.