AI Paper Atlas

Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes

Hyperspectral Recovery from RGB Images using Gaussian Processes

Naveed Akhtar, Ajmal Saeed Mian

TPAMI 2018 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Structured Gaussian process models · 142 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 Gaussian Processes instead of plain dictionary learning bases (ablation)Proposed (DL variant) · CAVE FeathersRMSE: 8.11 -> 7.89Improved
use Gaussian Processes instead of plain dictionary learning bases (ablation)Proposed (DL variant) · CAVE PeppersRMSE: 7.18 -> 5.74Improved
use Gaussian Processes instead of plain dictionary learning bases (ablation)Proposed (DL variant) · iCVL domain-specific BeachRMSE: 4.89 -> 4.33Improved
use Gaussian Processes instead of plain dictionary learning bases (ablation)Proposed (DL variant) · iCVL domain-specific ObjectsSAM: 1.10 -> 0.82Improved
replace Arad's sparse coding with the proposed GP methodArad · CAVEaverage RMSE: 16.35% reduction in RMSEImproved
replace Arad's method with the proposed GP methodArad · CAVEaverage SAM: 9.39% reductionImproved
replace A+ with the proposed GP methodA+ · CAVEaverage RMSE: 11.98% reductionImproved
replace Arad's method with the proposed GP methodArad · iCVL domain-specificaverage relative RMSE: 18.62% reductionImproved
replace Arad's method with the proposed GP methodArad · iCVL domain-specificaverage SAM: 23.35% reductionImproved
replace Arad's method with the proposed GP methodArad · Harvardaverage RMSE: 30.75% improvementImproved
train on a different scene domain than the test domain (ablation)Proposed · iCVL Floralrelative RMSE: 7.38 -> 9.44Hurt
train on a different scene domain than the test domain (ablation)Proposed · iCVL FloralSAM: 4.49 -> 5.28Hurt

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