AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Learning Graph Regularisation for Guided Super-Resolution

Riccardo de Lutio, Alexander Becker, Stefano D'Aronco, Stefania Russo, Jan D. Wegner, Konrad Schindler

CVPR 2022 · Graph learning › Graph self-supervised learning · approach: Multi-view graph clustering · 42 citations (OpenAlex)

Check 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 graph regularisation with an explicit source-fidelity optimisation layerguided depth super-resolution · Middlebury, NYUv2, and DIML at ×4, ×8, and ×16MSE: Middlebury: 3.60 -> 3.04 (×4), 9.48 -> 7.26 (×8), 30.6 -> 24.7 (×16); NYUv2: 6.85 -> 6.45 (×4), 24.1 -> 19.6 (×8), 84.5 Improved
train on NYUv2 and retain the explicit source-fidelity constraintOurs · DIML and Middlebury cross-dataset ×8low-resolution MSE: DIML: 2.4 · 10⁻³; Middlebury: 1.1 · 10⁻³Improved
replace learned features with raw Colour features (ablation)graph regularisation for guided depth super-resolution · NYUv2 ×8MSE: 19.6 -> 68.4Hurt
use UEfficientNet-B2 as the graph feature extractor (ablation)Ours · NYUv2 ×8MSE: 19.6 -> 24.9Hurt
use UResNet-18 instead of UResNet-50 as the graph feature extractor (ablation)Ours · NYUv2 ×8MSE: 19.6 -> 21.7Hurt
use FDSR features instead of UResNet-50 features (ablation)Ours · NYUv2 ×8MSE: 19.6 -> 30.4Hurt
use GDPT instead of UResNet-50 as the graph feature extractor (ablation)Ours · NYUv2 ×8MSE: 19.6 -> 22.3Hurt
increase feature extractor capacity from UResNet-18 to UResNet-50 (ablation)Ours · NYUv2 ×8MAE: 1.52 -> 1.42Improved

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