AI Paper Atlas

Research map / 3D vision / Depth and stereo

E-RGB-D: Real-Time Event-Based Perception with Structured Light

Seyed Ehsan Marjani Bajestani, Giovanni Beltrame

IJCV 2026 · 3D vision › Depth and stereo · approach: Spike and event camera reconstruction · 1 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 fewer lines (23 instead of 45) in the depth pattern (ablation)E-RGB-D mode 3 · Static scenesscan time: 12.57 ms -> 7.4 msImproved
fewer lines gives higher fill rate but less detail (ablation)E-RGB-D · Static scenesfill rate vs detailMixed
use mode 4 (same pattern for color and depth, projected three times) instead of mode 3 (ablation)E-RGB-D 23 lines · Static scenesscan time: 7.4 ms -> 17.23 msHurt
use event-based DLP structured light with direct disparity lookup instead of ESLdepth reconstruction · Static scenes (Duck, M4L23)reconstruction speed: about 90 times fasterImproved
use E-RGB-D instead of RealSense D455 for frame scan timeE-RGB-D · Dynamic scenesscan time: 33 ms -> 7.4 msImproved
denser patterns (higher coverage percentage) (ablation)E-RGB-D · Static scenesaccuracy vs FOVMixed
vary scanning speed and coverage percentage (ablation)E-RGB-D · Color PSNRANOVA F: Speed F = 11569.337 for color PSNR; CP F = 947.513Improved

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