Research map / Architectures and efficiency / RNNs and normalization
TINC: Tree-Structured Implicit Neural Compression
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 TINC instead of HEVC | Medical data compression · Medical data (high compression ratios) | PSNR (dB): 50.51 -> 50.59 | Helped |
| Use TINC instead of HEVC | Medical data compression · Medical data (all compression ratios) | PSNR (dB): 52.31 -> 52.02 | Hurt |
| Use TINC instead of HEVC | Medical data compression · Medical data (high compression ratios) | SSIM: 0.9877 -> 0.9878 | Helped |
| Use TINC instead of HEVC | Medical data compression · Medical data (all compression ratios) | SSIM: 0.9903 -> 0.9897 | Hurt |
| Use TINC instead of HEVC | Biological data compression · Biological data (high compression ratios) | Acc.200: 0.9917 -> 0.9934 | Helped |
| Use TINC instead of HEVC | Biological data compression · Biological data (all compression ratios) | Acc.200: 0.9955 -> 0.9945 | Hurt |
| Use TINC instead of HEVC | Biological data compression · Biological data (all compression ratios) | Acc.500: 0.9975 -> 0.9970 | Hurt |
| Use TINC instead of SCI | Biological data compression · Biological data (high compression ratios) | Acc.500: 0.9951 -> 0.9958 | Helped |
| Increase tree levels from 1 to 3 (ablation) | TINC · Medical data at 256× compression | SSIM | Helped |
| Increase tree levels under a high compression ratio (ablation) | TINC · Medical data at 512× compression | SSIM | Mixed |
| Allocate more parameters to shallow levels (ablation) | TINC · Brain subregions at 512× compression | SSIM | Mixed |
| Allocate parameters to shallow rather than deep levels (ablation) | TINC · Medical data | SSIM | Mixed |
Closest papers by meaning
- NVRC: Neural Video Representation Compression (NeurIPS 2024 · similarity 0.88)
- SINR: Sparsity Driven Compressed Implicit Neural Representations (CVPR 2025 · similarity 0.88)
- Towards Lossless Implicit Neural Representation via Bit Plane Decomposition (CVPR 2025 · similarity 0.86)
- Combining Frame and GOP Embeddings for Neural Video Representation (CVPR 2024 · similarity 0.85)
- Learning Transferable Features for Implicit Neural Representations (NeurIPS 2024 · similarity 0.85)
- Grids Often Outperform Implicit Neural Representation at Compressing Dense Signals (NeurIPS 2025 · 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.