AI Paper Atlas

Research map / 3D vision / Depth and stereo

Refining Geometry from Depth Sensors using IR Shading Images

Gyeongmin Choe, Jaesik Park, Yu‐Wing Tai, In So Kweon

IJCV 2016 · 3D vision › Depth and stereo · approach: Photometric stereo · 36 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 analytic Jacobian instead of numerical Jacobian in the mesh optimization (ablation)IR shading geometry refinement · Cicerofinal mean cost error / wave artifactsImproved
add multiple (36) IR shading images instead of a single image (ablation)IR shading geometry refinement · Ciceromesh quality (qualitative)Improved
refine Kinect fusion mesh with IR shadingKinect fusion mesh · Cicero (Kinect I), distance to ground truthaverage distance error (mm): 2.041 -> 2.010mmImproved
refine mesh with IR shading imagesKinect fusion mesh · User study, 21 subjects, all real-world datasetspreference over Kinect fusionImproved
refine mesh with IR shading imagesKinect fusion mesh · held-out view renderingRMSEImproved
use a single IR image on ornamental stoneIR shading geometry refinement · Ornamental stonegeometry at other viewpointsHurt

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