Research map / Image generation / Super-resolution
B-Spline Texture Coefficients Estimator for Screen Content Image Super-Resolution
Byeonghyun Pak, Jaewon Lee, Kyong Hwan Jin
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 |
|---|---|---|---|
| Use B-spline features instead of Fourier features | BTC versus LTE · SCI1K test ×4 | PSNR (dB): 30.93 -> 31.10 | Improved |
| Use B-spline features instead of Fourier features | BTC versus LTE · SCID ×4 | PSNR (dB): 26.34 -> 26.30 | Hurt |
| Add the coefficient estimator (ablation) | BTC · SCI1K test ×4 | PSNR (dB): 30.96 -> 31.10 | Improved |
| Add the knot estimator (ablation) | BTC · SCI1K test ×4 | PSNR (dB): 27.42 -> 31.10 | Improved |
| Add the dilation estimator (ablation) | BTC · SCI1K test ×4 | PSNR (dB): 30.94 -> 31.10 | Improved |
| Add the LR skip connection (ablation) | BTC · SCI1K test ×4 | PSNR (dB): 30.49 -> 31.10 | Improved |
| Use a third-order rather than second-order B-spline basis (ablation) | BTC · SCI1K test ×4 | PSNR (dB): 30.91 -> 31.10 | Improved |
| Use a third-order rather than fourth-order B-spline basis (ablation) | BTC · SCI1K test ×4 | PSNR (dB): 31.04 -> 31.10 | Improved |
| Use BTC rather than LTE | super-resolution on natural-image benchmarks · Set5, Set14, B100, Urban100 | PSNR (dB) | Mixed |
Closest papers by meaning
- Implicit Transformer Network for Screen Content Image Continuous Super-Resolution (NeurIPS 2021 · similarity 0.88)
- Learning Re-sampling Methods with Parameter Attribution for Image Super-resolution (NeurIPS 2023 · similarity 0.83)
- Auto-Encoded Supervision for Perceptual Image Super-Resolution (CVPR 2025 · similarity 0.83)
- BF-STVSR: B-Splines and Fourier---Best Friends for High Fidelity Spatial-Temporal Video Super-Resolution (CVPR 2025 · similarity 0.83)
- Training Generative Image Super-Resolution Models by Wavelet-Domain Losses Enables Better Control of Artifacts (CVPR 2024 · similarity 0.82)
- Beyond Image Super-Resolution for Image Recognition with Task-Driven Perceptual Loss (CVPR 2024 · similarity 0.82)
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.
