AI Paper Atlas

Research map / 3D vision / Depth and stereo

Filter Selection for Hyperspectral Estimation

Boaz Arad, Ohad Ben-Shahar

ICCV 2017 · 3D vision › Depth and stereo · approach: Depth from light field and defocus · 55 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
select the best consumer camera filters instead of the worstArad and Ben-Shahar method · 28 consumer camerasRRMSE: 0.160 -> 0.127 (20.6% improvement)Improved
select the best consumer camera filters instead of the worstNguyen et al. method · 28 consumer camerasRRMSE: 0.293 -> 0.238 (18.7% improvement)Improved
use an optimal generic Midopt filter set instead of the best consumer cameraArad and Ben-Shahar method · Midopt filter spaceRRMSE: 0.127 -> 0.116Improved
combine filters from different cameras instead of one cameraArad and Ben-Shahar method · commercial camera filter spaceRRMSE: 0.127 -> 0.119Improved
use a large OMEGA filter space instead of the commercial camera filter spaceArad and Ben-Shahar method · OMEGA filter spaceRRMSE: 0.119 -> 0.107Improved
use evolutionary optimization instead of exhaustive searchfilter set selection · commercial camera filter spaceevaluations needed: 95284 -> less than 13800 filter setsImproved
use evolutionary optimization instead of random searchfilter set selection · OMEGA filter spaceevaluations to reach RRMSE 0.107: 344,600 -> 39,595Improved
evaluate filter sets on a 2.5 million pixel random subset instead of the full test set (ablation)filter set selection · BGU HS databaseRRMSENo clear effect
use optimal custom filter set from OMEGA instead of consumer camera Olympus E-PL2Arad and Ben-Shahar method · BGU HS databaseRRMSE reduction: at least 33.1%Improved

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