AI Paper Atlas

Research map / Image generation / Super-resolution

Binarized Neural Network for Single Image Super Resolution

Jingwei Xin, Nannan Wang, Xinrui Jiang, Jie Li, Heng Huang, Xinbo Gao

ECCV 2020 · Image generation › Super-resolution · approach: CNN and transformer SR architectures · 80 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
add bit accumulation mechanism (BAM) instead of ABCSRResNet · Set5 x4PSNR (dB): 30.78 -> 31.24Improved
add BAM instead of DoReFaSRResNet · Urban100 x4PSNR (dB): 24.45 -> 24.95Improved
add BAM instead of ABCVDSR · Set5 x4PSNR (dB): 29.59 -> 30.31Improved
add BAM instead of BNNVDSR · Set5 x4PSNR (dB): 29.02 -> 30.31Improved
use the BSRN lightweight architecture instead of SRResNet with BAMBAM · Set5 x4PSNR (dB): 31.24 -> 31.35Improved
add linear combination coefficients in weight quantization (ablation)BSRN · Set5 x4PSNR (dB): 31.25 -> 31.35Improved
add bit accumulation in weight quantization (ablation)BSRN · Set5 x4PSNR (dB): 31.14 -> 31.35Improved
add linear combination coefficients in activation quantization (ablation)BSRN · Set5 x4PSNR (dB): 31.22 -> 31.35Improved
add bit accumulation in activation quantization (ablation)BSRN · Set5 x4PSNR (dB): 30.92 -> 31.35Improved
use BAM with binary filters instead of Ma et al. quantizationSRResNet · Set5 x4PSNR (dB): 30.34 -> 31.57Improved

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