atlas

Research map / 3D vision / Depth and stereo

Polka Lines: Learning Structured Illumination and Reconstruction for Active Stereo

CVPR 2021 · 3D vision › Depth and stereo · approach: Neural light field and illumination imaging · 31 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
Optimize the illumination pattern jointly with the reconstruction network instead of using a hand-crafted patternActive stereo · Synthetic indoor environmentsdepth reconstruction accuracyHelped
Use the learned Polka Lines pattern instead of the Intel RealSense D415 patternActive stereo · High dynamic range scenesdepth reconstruction robustnessHelped
Add illumination-image features and narrow-baseline cues to the binocular camera inputs (ablation)Trinocular active stereo network · Occluded regionsdepth estimation stabilityHelped
Add a Polka Lines illumination pattern to passive stereoActive stereo · High dynamic range scene conditionsdepth estimation accuracyHelped
Use a generic-environment pattern rather than an indoor-specific patternPolka Lines active stereo · Low-reflectance objectsdepth estimation accuracyHelped

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