AI Paper Atlas

Research map / Image generation / Image restoration

Learning Steerable Function for Efficient Image Resampling

Jiacheng Li, Chang Chen, Wei Huang, Zhiqiang Lang, Fenglong Song, Youliang Yan, Zhiwei Xiong

CVPR 2023 · Image generation › Image restoration · approach: Inverse imaging with learned priors · 13 citations (OpenAlex)

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 changedWhereMeasuredEffect
Use locally adapted steerable resampling functionsLeRF · Set5, ×2 upsamplingPSNR: 35.71 vs 30.75Improved
Replace the steerable Gaussian with learned isotropic Keys cubic (ablation)LeRF · Set5, ×2 upsamplingPSNR: 35.71 vs 34.68Hurt
Train on ×2 rather than ×4 downsampled pairs (ablation)LeRF · Set5, ×2 upsamplingPSNR: 35.71 vs 35.67No clear effect
Train on mixed-scale data pairs (ablation)LeRF · Set5, ×2 upsamplingPSNR: 35.71 vs 35.67No clear effect
Remove LUT acceleration and use the learned network (ablation)LeRF · Set5, ×2 upsamplingPSNR: 35.71 vs 36.11Improved
Add LUT acceleration (ablation)LeRF · Set5, ×2 upsamplingMACs: 21.75G vs 57.94MImproved
Add directional ensemble instead of rotation ensemble (ablation)LeRF · Set5, ×2 upsamplingPSNR: 34.44 vs 35.71Improved
Add edge-sensitive “C” and “X” indexing patterns (ablation)LeRF · Set5, ×2 upsamplingPSNR: 34.90 vs 35.71Improved
Add the pre-filtering stage (ablation)LeRF · Set5, ×2 upsamplingPSNR: 34.43 vs 35.71Improved
Add adaptive resampling functions after pre-filtering (ablation)pre-filtering-only variant · Set5, ×2 upsamplingPSNR: 34.69 vs 35.71Improved
Use LeRF instead of bicubic interpolationSet14 ×4 upsampling · Set14, ×4 upsamplingrunning time: 126 -> 110Improved
Use LeRF instead of LIIFSet14 ×4 upsampling · Set14, ×4 upsamplingPSNR: 28.65 vs 27.35Hurt

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy