AI Paper Atlas

Research map / 3D vision / Depth and stereo

Reconstruction-based Pairwise Depth Dataset for Depth Image Enhancement Using CNN

Junho Jeon, Seungyong Lee

ECCV 2018 · 3D vision › Depth and stereo · approach: Dense depth prediction and completion · 39 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
filter misaligned training pairs by SSIM (< 0.8) and large holes (ablation)LapDEN · ScanNet trainingtraining stability / lossImproved
add dataset filtering of misaligned pairs (ablation)LapDEN · ScanNet patches (qualitative)edge sharpnessImproved
add gradient-based structure preserving loss L_S (ablation)LapDEN · ScanNet patches (qualitative)edge sharpnessImproved
use LapDEN instead of rolling guidance filterRGF · ScanNet testSSIM: 0.9065 -> 0.9229Improved
use LapDEN instead of rolling guidance filterRGF · ScanNet testRMSE: 0.2401 -> 0.2148Improved
use LapDEN instead of mutual-structure joint filterJoint filter · ScanNet testSSIM: 0.9152 -> 0.9229Improved
use LapDEN instead of mutual-structure joint filterJoint filter · ScanNet testRMSE: 0.2360 -> 0.2148Improved
enhance raw depth with LapDENraw depth · ScanNet testRMSE: 0.3450 -> 0.2148Improved
pre-filter depth stream with LapDEN before dense 3D reconstructionBundleFusion · ScanNet scenes (qualitative)convergence speedImproved
pre-filter depth stream and skip every other frameBundleFusion · ScanNet scenes (qualitative)reconstruction qualityNo clear effect

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