Research map / 3D vision / Face and shape
Cross-Frequency Implicit Neural Representation With Self-Evolving Parameters
Chang Yu, Yisi Luo, Kai Ye, Xile Zhao, Deyu Meng
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 |
|---|---|---|---|
| apply the Haar-wavelet cross-frequency INR (CF-INR) on top of PE-INR | PE-INR · Color image House | PSNR: 32.14 -> 41.40 | Improved |
| apply CF-INR on top of WIRE-INR | WIRE-INR · Color image House | PSNR: 36.95 -> 42.69 | Improved |
| apply CF-INR on top of FINER-INR | FINER-INR · Color image House | PSNR: 39.18 -> 51.55 | Improved |
| apply CF-INR on top of SIREN-INR | SIREN-INR · Color image House | PSNR: 37.91 -> 51.64 | Improved |
| apply CF-INR on top of SIREN-INR | SIREN-INR · Color image Mandrill | PSNR: 29.56 -> 47.84 | Improved |
| apply CF-INR on top of SIREN-INR | SIREN-INR · MSI Flowers | PSNR: 47.47 -> 57.29 | Improved |
| apply CF-INR on top of PE-INR | PE-INR · MSI Painting | PSNR: 38.47 -> 50.66 | Improved |
| apply CF-INR on top of FINER-INR | FINER-INR · MSI Flowers | SSIM: 0.992 -> 0.995 | No clear effect |
| apply CF-INR on top of SIREN-INR | SIREN-INR · Color image Airplane | SSIM: 0.962 -> 0.998 | Improved |
| use CF-INR tensor decomposition instead of MLP-based INR for fitting | SIREN · MSI 256x256x31 regression | running time (5000 iterations): 117.2s -> 36.6s | Improved |
| use CF-INR tensor decomposition instead of MLP-based INR for fitting | SIREN · MSI 256x256x31 regression | FLOPs: 13438.6M -> 103.2M | Improved |
| use theoretical power exponent 1/2 for updating frequency parameters instead of other exponents (ablation) | CF-INR self-evolving omega · image fitting | 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.
- PE-INR — PEINR: A Physics-enhanced Implicit Neural Representation for High-Fidelity Flow Field Reconstruction (ICML 2025) · better on 4 of 4 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
- FreSh: Frequency Shifting for Accelerated Neural Representation Learning (ICLR 2025 · similarity 0.86)
- Implicit Neural Representations and the Algebra of Complex Wavelets (ICLR 2024 · similarity 0.85)
- Inductive Gradient Adjustment for Spectral Bias in Implicit Neural Representations (ICML 2025 · similarity 0.85)
- Grids Often Outperform Implicit Neural Representation at Compressing Dense Signals (NeurIPS 2025 · similarity 0.85)
- MIRE: Matched Implicit Neural Representations (CVPR 2025 · similarity 0.85)
- Learning Spatially Collaged Fourier Bases for Implicit Neural Representation (AAAI 2024 · similarity 0.85)
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.
