Research map / 3D vision / Face and shape
SL2A-INR: Single-Layer Learnable Activation for Implicit Neural Representation
Reza Rezaeian, Moein Heidari, Reza Azad, Dorit Merhof, Hamid Soltanian-Zadeh, Ilker Hacihaliloglu
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 SL2A instead of FINER for image fitting | INR · DIV2K image fitting (average) | PSNR (dB): 36.35 -> 36.88 | Improved |
| use SL2A instead of FINER for image fitting | INR · DIV2K image fitting (average) | SSIM: 0.924 -> 0.933 | Improved |
| use SL2A instead of FINER for SDF | INR · SDF Lucy | IoU: 9.832e-1 -> 9.988e-1 | Improved |
| use SL2A instead of FINER for NeRF | INR · Blender Materials | PSNR: 27.05 -> 28.62 | Improved |
| use SL2A instead of FINER for NeRF | INR · Blender Drums | PSNR: 24.90 -> 24.33 | Hurt |
| use SL2A instead of FINER for NeRF | INR · Blender Ficus | PSNR: 28.70 -> 28.31 | Hurt |
| add skip connections from the LA block to the Fusion block (ablation) | SL2A · DIV2K image fitting | PSNR | Improved |
| increase Chebyshev polynomial degree K from 128 to 512 (ablation) | SL2A · DIV2K image fitting | PSNR | Improved |
| add skip connections (NTK analysis) (ablation) | SL2A · NTK eigenvalues | eigenvalue decay | Improved |
| increase K in the LA block (NTK analysis) (ablation) | SL2A · NTK eigenvalues | eigenvalue decay | Improved |
| use SL2A instead of other INRs under varied LR and batch size | INR · DIV2K robustness heatmap | mean PSNR | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- FINER — FINER: Flexible Spectral-bias Tuning in Implicit NEural Representation by Variable-periodic Activation Functions (CVPR 2024) · better on 12 of 15 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- VI^3NR: Variance Informed Initialization for Implicit Neural Representations (CVPR 2025 · similarity 0.89)
- Implicit Representations via Operator Learning (ICML 2024 · similarity 0.88)
- ReLUs Are Sufficient for Learning Implicit Neural Representations (ICML 2024 · similarity 0.87)
- MIRE: Matched Implicit Neural Representations (CVPR 2025 · similarity 0.87)
- Improved Implicit Neural Representation with Fourier Reparameterized Training (CVPR 2024 · similarity 0.87)
- Implicit Neural Representations and the Algebra of Complex Wavelets (ICLR 2024 · similarity 0.86)
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.
