AI Paper Atlas

Research map / Image generation / Image restoration

LeRF: Learning Resampling Function for Adaptive and Efficient Image Interpolation

Jiacheng Li, Chang Chen, Fenglong Song, Youliang Yan, Zhiwei Xiong

TPAMI 2025 · Image generation › Image restoration · approach: Inverse imaging with learned priors · 5 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 learned anisotropic adaptive Gaussian instead of fixed Gaussian (ablation)LeRF-G · Set5 x2PSNR: 30.75 -> 35.71Improved
use adaptive anisotropic Gaussian instead of isotropic Keys cubic (ablation)LeRF-G · Set5 x2PSNR: 34.68 -> 35.71Improved
add LUT acceleration to LeRF-G (ablation)LeRF-G · Set5 x2PSNR: 36.11 -> 35.71Mixed
add DE (directional encoding) instead of RE (ablation)LeRF-G · Set5 x2PSNR: 34.44 -> 35.71Improved
add CX pattern (ablation)LeRF-G · Set5 x2PSNR: 34.90 -> 35.71Improved
add pre-processing stage (ablation)LeRF-G · Set5 x2PSNR: 34.43 -> 35.71Improved
train on x2 data instead of x4 data (ablation)LeRF-G · Set5 x4PSNR: 30.15 -> 29.91Hurt
train on mixed-scale data instead of x4 data (ablation)LeRF-G · Set5 x3PSNR: 32.02 -> 32.26No clear effect
replace LUT multi-branch DNN with convolution-only LeRF-Net (ablation)LeRF-Net · Set5 x2PSNR: 36.11 -> 36.23Improved
increase channels from 16 to 64 (ablation)LeRF-Net · Set5 x2PSNR: 36.44 -> 36.57Improved
increase channels from 64 to 96 (ablation)LeRF-Net · Set5 x2PSNR: 36.57 -> 36.52No clear effect
combine LeRF-G with SR-LUTSR-LUT · Set5 x2PSNR: 35.53 -> 35.53No clear effect

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