AI Paper Atlas

Research map / Image generation / Super-resolution

Learning Mutual Modulation for Self-Supervised Cross-Modal Super-Resolution

Xiaoyu Dong, Naoto Yokoya, Longguang Wang, Tatsumi Uezato

ECCV 2022 · Image generation › Super-resolution · approach: Efficient lightweight super-resolution · 23 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 guide-to-source modulation (ablation)MMSR · Middlebury 2014 x8 depth SRRMSE: 4.30 -> 4.08Improved
add source-to-guide modulation (ablation)MMSR · Middlebury 2014 x8 depth SRRMSE: 4.30 -> 3.72Improved
add both modulations (mutual) (ablation)MMSR · Middlebury 2014 x8 depth SRRMSE: 4.30 -> 3.67Improved
add cross-domain filtering to adaptive filters (ablation)MMSR · Middlebury 2014 x8 depth SRRMSE: 3.84 -> 3.67Improved
add adaptive filtering to cross-domain filters (ablation)MMSR · Middlebury 2014 x8 depth SRRMSE: 4.88 -> 3.67Improved
add cross-domain filtering alone (ablation)MMSR · Middlebury 2014 x8 depth SRRMSE: 4.87 -> 4.88No clear effect
enlarge neighborhood size from 3x3 to 11x11 in both modulations (ablation)MMSR · Middlebury 2014 x8 depth SRRMSE: 4.23 -> 3.67Improved
enlarge neighborhood size from 7x7 to 11x11 in both modulations (ablation)MMSR · Middlebury 2014 x8 depth SRRMSE: 3.91 -> 3.67Improved
fuse with 1x1 conv instead of naive summation (ablation)MMSR · Middlebury 2003 x4 depth SRRMSE: 1.88 -> 1.78Improved
fuse with 1x1 conv instead of attention plus summation (ablation)MMSR · Middlebury 2003 x4 depth SRRMSE: 1.92 -> 1.78Improved
fuse with 1x1 conv instead of attention plus 1x1 conv (ablation)MMSR · Middlebury 2003 x4 depth SRRMSE: 1.84 -> 1.78Improved

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