Research map / 3D vision / Face and shape
Learning Continuous Image Representation With Local Implicit Image Function
Check 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 LIIF instead of MetaSR with the EDSR-baseline encoder | EDSR-baseline · DIV2K validation ×30 | PSNR (dB): 20.37 -> 20.48 | Helped |
| Use LIIF instead of MetaSR with the RDN encoder | RDN · DIV2K validation ×30 | PSNR (dB): 20.47 -> 20.59 | Helped |
| Use LIIF rather than resizing ground-truths to one fixed size | CelebAHQ size-varied image-to-image learning · CelebAHQ L=64, H=128 | PSNR (dB): 34.78 -> 35.96 | Helped |
| Use LIIF rather than resizing ground-truths to one fixed size | CelebAHQ size-varied image-to-image learning · CelebAHQ L=32, H=256 | PSNR (dB): 27.56 -> 27.74 | Helped |
| Add cell decoding (ablation) | LIIF · DIV2K validation ×4 | PSNR (dB): 28.97 -> 29.00 | Helped |
| Add cell decoding (ablation) | LIIF · DIV2K validation ×30 | PSNR (dB): 20.51 -> 20.48 | Hurt |
| Add feature unfolding (ablation) | LIIF · DIV2K validation ×30 | PSNR (dB): 20.47 -> 20.48 | No clear effect |
| Add local ensemble (ablation) | LIIF · DIV2K validation ×30 | PSNR (dB): 20.45 -> 20.48 | Helped |
| Use a 5-layer rather than 3-layer decoder (ablation) | LIIF · DIV2K validation ×30 | PSNR (dB): 20.42 -> 20.48 | Helped |
| Train at one fixed scale rather than random scales ×1–×4 (ablation) | LIIF · DIV2K validation ×4 | PSNR (dB): 29.00 -> 28.77 (×2-only); 29.00 -> 28.99 (×3-only); 29.00 -> 29.00 (×4-only) | Mixed |
| Train at ×4 only instead of random scales ×1–×4 (ablation) | LIIF · DIV2K validation ×30 | PSNR (dB): 20.48 -> 20.51 | Helped |
Closest papers by meaning
- HIIF: Hierarchical Encoding based Implicit Image Function for Continuous Super-resolution (CVPR 2025 · similarity 0.89)
- LISR: Learning Linear 3D Implicit Surface Representation Using Compactly Supported Radial Basis Functions (AAAI 2024 · similarity 0.85)
- Learning Spatially Collaged Fourier Bases for Implicit Neural Representation (AAAI 2024 · similarity 0.84)
- Progressive Fourier Neural Representation for Sequential Video Compilation (ICLR 2024 · similarity 0.84)
- Latent Modulated Function for Computational Optimal Continuous Image Representation (CVPR 2024 · similarity 0.83)
- Sharpening Neural Implicit Functions with Frequency Consolidation Priors (AAAI 2025 · similarity 0.83)
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.