Research map / Architectures and efficiency / Attention and transformers
Locality-Aware Generalizable Implicit Neural Representation
Doyup Lee, Chiheon Kim, Minsu Cho, Wook-Shin Han
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 selective token aggregation (vs IPC weight modulation) (ablation) | Locality-aware INR · ImageNette 178x178 | PSNR: 34.54 -> 37.46 | Improved |
| add multi-band feature modulation (vs simple MLP stack) (ablation) | Locality-aware INR · ImageNette 178x178 | PSNR: 33.90 -> 37.46 | Improved |
| add selective token aggregation (ablation) | Locality-aware INR · ShapeNet Lamp 3 views | PSNR: 25.31 -> 26.00 | Improved |
| add multi-band feature modulation (ablation) | Locality-aware INR · ShapeNet Lamp 3 views | PSNR: 25.78 -> 26.00 | Improved |
| add selective token aggregation (ablation) | Locality-aware INR · FFHQ 256x256 | PSNR: 34.52 -> 38.01 | Improved |
| add multi-band feature modulation (ablation) | Locality-aware INR · FFHQ 256x256 | PSNR: 33.65 -> 38.01 | Improved |
| reverse bandwidth order to (32,128) (ablation) | Locality-aware INR · ImageNette 178x178 | PSNR: 37.46 -> 35.00 | Hurt |
| use equal bandwidths (128,128) (ablation) | Locality-aware INR · ImageNette 178x178 | PSNR: 37.46 -> 35.30 | Hurt |
| raise query bandwidth sigma_q from 16 to 128 (ablation) | Locality-aware INR · ImageNette 178x178 | PSNR: 37.46 -> 35.58 | Hurt |
| increase modulation levels from L=1 to L=3 (ablation) | Locality-aware INR · FFHQ 256x256 | PSNR: 37.09 -> 40.13 | Improved |
| increase modulation levels from L=3 to L=4 (ablation) | Locality-aware INR · FFHQ 256x256 | PSNR: 40.13 -> 39.79 | No clear effect |
| add linear layers in selective token aggregation (ablation) | Locality-aware INR · ImageNette 178x178 | PSNR: 31.57 -> 37.46 | Improved |
Closest papers by meaning
- Implicit Representations via Operator Learning (ICML 2024 · similarity 0.89)
- Towards Croppable Implicit Neural Representations (NeurIPS 2024 · similarity 0.89)
- Learning Transferable Features for Implicit Neural Representations (NeurIPS 2024 · similarity 0.88)
- SINR: Sparsity Driven Compressed Implicit Neural Representations (CVPR 2025 · similarity 0.88)
- Grids Often Outperform Implicit Neural Representation at Compressing Dense Signals (NeurIPS 2025 · similarity 0.87)
- VI^3NR: Variance Informed Initialization for Implicit Neural Representations (CVPR 2025 · similarity 0.87)
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.
