Research map / 3D vision / Face and shape
Calibrated Harmonic Overlaid Implicit Neural Representations for Multi-Dimensional Data
Honghang Chen, XIUJUN ZHANG, Xiaoli Sun, MINGQING XIAO
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 CHS (additive harmonic superposition) to sine INR (ablation) | CHOIR / sine INR · MSI Flowers (Random OR=0.10) | PSNR: 33.500 -> 39.136 | Improved |
| add CHS to sine INR (ablation) | CHOIR / sine INR · MSI Flowers (Scene 3) | PSNR: 26.238 -> 32.296 | Improved |
| add PSC with gamma 1/8 to sine INR (ablation) | CHOIR / sine INR · MSI Flowers (Random OR=0.10) | PSNR: 33.500 -> 40.335 | Improved |
| reduce PSC frequency scale gamma from 1.0 to 1/8 (ablation) | CHOIR / sine INR · MSI Flowers (Random OR=0.10) | PSNR: 37.251 -> 40.335 | Improved |
| reduce gamma further from 1/8 to 1/16 (ablation) | CHOIR / sine INR · MSI Flowers (Random OR=0.10) | PSNR: 40.335 -> 38.629 | Hurt |
| combine CHS and PSC vs PSC alone (ablation) | CHOIR / sine INR · MSI Flowers (Random OR=0.10) | PSNR: 40.335 -> 41.316 | Improved |
| combine CHS and PSC vs CHS alone (ablation) | CHOIR / sine INR · MSI Flowers (Scene 3) | PSNR: 32.296 -> 32.605 | Improved |
| increase network depth for SIREN/FINER/FreSh (ablation) | CHOIR / sine INR · depth sweep (MSI Flowers OR=0.30) | PSNR | Hurt |
| increase network depth for CHOIR up to 15 layers (ablation) | CHOIR / sine INR · depth sweep (MSI Flowers OR=0.30) | PSNR | Improved |
| CHOIR vs best baseline on NeRF Blender Lego (ablation) | CHOIR / sine INR · NeRF Blender Lego | PSNR: 25.340 -> 28.299 | 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 1 of 1 shared result
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
- FINER: Flexible Spectral-bias Tuning in Implicit NEural Representation by Variable-periodic Activation Functions (CVPR 2024 · similarity 0.87)
- Inductive Gradient Adjustment for Spectral Bias in Implicit Neural Representations (ICML 2025 · similarity 0.86)
- FreSh: Frequency Shifting for Accelerated Neural Representation Learning (ICLR 2025 · similarity 0.85)
- VI^3NR: Variance Informed Initialization for Implicit Neural Representations (CVPR 2025 · similarity 0.85)
- Grids Often Outperform Implicit Neural Representation at Compressing Dense Signals (NeurIPS 2025 · similarity 0.85)
- Improved Implicit Neural Representation with Fourier Reparameterized Training (CVPR 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.
