AI Paper Atlas

Research map / 3D vision / Depth and stereo

Real-time high speed motion prediction using fast aperture-robust event-driven visual flow

Himanshu Akolkar, Sio-Hoï Ieng, Ryad Benjamin Benosman

TPAMI 2020 · 3D vision › Depth and stereo · approach: Learned optical and scene flow · 65 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
add multi-scale max-pooling direction correction (ARMS) to plane-fitting flowEDL plane-fitting flow · MVSEC Indoor Flying 1AEE (pixels): 2.45 -> 1.52Improved
add multi-scale max-pooling direction correction (ARMS) to plane-fitting flowEDL plane-fitting flow · MVSEC Indoor Flying 2AEE (pixels): 2.42 -> 1.59Improved
add multi-scale max-pooling direction correction (ARMS) to plane-fitting flowEDL plane-fitting flow · MVSEC Indoor Flying 3AEE (pixels): 5.35 -> 1.89Improved
add multi-scale max-pooling direction correction (ARMS) to plane-fitting flowEDL plane-fitting flow · MVSEC Outdoor DayAEE (pixels): 3.87 -> 2.75Improved
add multi-scale max-pooling direction correction (ARMS) to plane-fitting flowEDL plane-fitting flow · MVSEC Outdoor NightAEE (pixels): 5.53 -> 4.47Improved
use ARMS flow instead of EDL flow for 250 ms event predictionevent prediction of moving square · Moving square, 250 ms predictionmean translation error (pixels per event): 8.70 -> 6.52Improved
use ARMS flow instead of EDL flow for 250 ms event predictionevent prediction of moving square · Moving square, 250 ms predictionscaling error: 0.141 -> 0.085Improved
use ARMS flow instead of EDL flow for 500 ms event predictionpedestrian prediction · Pedestrian on street, 500 ms predictionmean translation error (pixels): 7.1240 -> 4.7558Improved
use ARMS flow instead of EDL flow for 500 ms event predictionpedestrian prediction · Pedestrian on street, 500 ms predictionscaling error: 0.297 -> 0.167Improved
ARMS flow versus learned EV-FlowNet (uses events plus grayscale)ARMS flow · MVSEC Indoor Flying 1-3AEE (pixels): 1.03 -> 1.52Mixed

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