Research map / Architectures and efficiency / RNNs and normalization
SCI: A Spectrum Concentrated Implicit Neural Compression for Biomedical Data
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 SCI instead of HEVC | Biomedical compression · Heart | PSNR: 61.54 -> 63.23 | Helped |
| Use SCI instead of HEVC | Biomedical compression · Lung | PSNR: 46.15 -> 45.63 | Hurt |
| Use SCI instead of HEVC | Biomedical compression · Kidney | PSNR: 50.09 -> 50.15 | Helped |
| Use SCI instead of HEVC | Biomedical compression · Brain | PSNR: 50.31 -> 50.82 | Helped |
| Use SCI instead of the strongest listed INR baseline | Biomedical compression · Neurons | Accuracy (200): 0.9983 -> 0.9986 | Helped |
| Use SCI instead of the strongest listed INR baseline | Biomedical compression · Vessels | Accuracy (200): 0.9913 -> 0.9944 | Helped |
| Add adaptive spectrum-based partitioning rather than equidistant partitioning (ablation) | SCI · Medical data | PSNR: 48.67 -> 49.29 | Helped |
| Add adaptive spectrum-based partitioning rather than no partitioning (ablation) | SCI · Medical data | PSNR: 47.76 -> 49.29 | Helped |
| Use a wider first layer with fr>1 rather than fr=1.0 (ablation) | SCI · Biological data | Accuracy (200): 0.9537 -> 0.9752 | Helped |
| Use a wider first layer with fr>1 rather than fr<1.0 (ablation) | SCI · Biological data | Accuracy (200): 0.9354 -> 0.9752 | Helped |
| Allocate parameters proportional to block size and inverse spectrum concentration rather than block size only (ablation) | SCI · Medical data | PSNR: 49.01 -> 49.29 | Helped |
| Allocate parameters proportional to block size and inverse spectrum concentration rather than inverse spectrum concentration only (ablation) | SCI · Medical data | PSNR: 48.82 -> 49.29 | Helped |
Closest papers by meaning
- A Compact Implicit Neural Representation for Efficient Storage of Massive 4D Functional Magnetic Resonance Imaging (AAAI 2025 · similarity 0.88)
- SINR: Sparsity Driven Compressed Implicit Neural Representations (CVPR 2025 · similarity 0.87)
- Grids Often Outperform Implicit Neural Representation at Compressing Dense Signals (NeurIPS 2025 · similarity 0.86)
- NVRC: Neural Video Representation Compression (NeurIPS 2024 · similarity 0.85)
- RECOMBINER: Robust and Enhanced Compression with Bayesian Implicit Neural Representations (ICLR 2024 · similarity 0.84)
- Combining Frame and GOP Embeddings for Neural Video Representation (CVPR 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.