Research map / Architectures and efficiency / RNNs and normalization
Implicit Neural Representations with Levels-of-Experts
Zekun Hao, Arun Mallya, Serge Belongie, Ming-Yu Liu
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 |
|---|---|---|---|
| use position-dependent hierarchical tiled weights instead of fixed weights with sine-cosine positional encoding | MLP · 64MP image fitting | PSNR: 32.34 -> 44.24 | Improved |
| replace learned coordinate embedding grid with tiled weights | PE + CE · 64MP image fitting | PSNR: 39.65 -> 44.24 | Improved |
| periodic tiling without multi-scale arrangement (interleaved) (ablation) | LoE · 64MP image fitting | PSNR: 44.24 -> 33.80 | Hurt |
| partition input into uniform chunks with independent MLPs (ablation) | LoE · 64MP image fitting | PSNR: 44.24 -> 43.13 | Hurt |
| random affine weight tiling (ablation) | LoE · 64MP image fitting | PSNR: 44.24 -> 42.08 | Hurt |
| feed a constant vector instead of positional encoding (ablation) | LoE · 64MP image fitting | PSNR: 44.24 -> 39.48 | Hurt |
| bilinear interpolation of weights instead of piecewise constant (ablation) | LoE · 64MP image fitting | PSNR: 44.24 -> 44.85 | No clear effect |
| quadruple hidden channels of SIREN (SIREN-L) (ablation) | SIREN · Video fitting | PSNR: 29.13 -> 37.71 | Improved |
| tiled weights instead of SIREN-L at similar MACs | SIREN-L · Video fitting | PSNR: 37.71 -> 39.98 | Improved |
| tiled weights instead of coordinate embedding | PE + CE · Video fitting | PSNR: 35.83 -> 39.98 | Improved |
| tiled weights without hierarchical arrangement (ablation) | LoE · Novel view synthesis (Family) | PSNR: 31.46 -> 27.73 | Hurt |
| hierarchical tiled weights instead of PE MLP | MLP · Novel view synthesis (Family) | PSNR: 30.50 -> 31.46 | Improved |
Closest papers by meaning
- Coordinate-Aware Modulation for Neural Fields (ICLR 2024 · similarity 0.85)
- Representing Sounds as Neural Amplitude Fields: A Benchmark of Coordinate-MLPs and a Fourier Kolmogorov-Arnold Framework (AAAI 2025 · similarity 0.85)
- Neural Experts: Mixture of Experts for Implicit Neural Representations (NeurIPS 2024 · similarity 0.84)
- MIRE: Matched Implicit Neural Representations (CVPR 2025 · similarity 0.84)
- Synergistic Integration of Coordinate Network and Tensorial Feature for Improving Neural Radiance Fields from Sparse Inputs (ICML 2024 · similarity 0.83)
- Adaptive Wavelet-Positional Encoding for High-Frequency Information Learning in Implicit Neural Representation (AAAI 2025 · similarity 0.83)
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.
