AI Paper Atlas

Research map / 3D vision / Depth and stereo

Learning an Event Sequence Embedding for Dense Event-Based Deep Stereo

Stepan Tulyakov, Francois Fleuret, Martin Kiefel, Peter Gehler, Michael Hirsch

ICCV 2019 · 3D vision › Depth and stereo · approach: Learned stereo with specialized sensors · 114 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
replace hand-crafted temporal aggregation with a continuous fully-connected layer (ablation)DDES · Indoor Flying split 1mean depth error (cm): 16.5 -> 13.6Improved
replace hand-crafted temporal aggregation with a continuous fully-connected layer (ablation)DDES · Indoor Flying split 1one-pixel accuracy (%): 87.3 -> 91.3Improved
use continuous fully-connected layer instead of temporal convolutional network (ablation)DDES · Indoor Flying split 1mean depth error (cm): 13.8 -> 13.6Improved
use continuous fully-connected layer instead of temporal convolutional network (ablation)DDES · Indoor Flying split 1one-pixel accuracy (%): 90.7 -> 91.3Improved
train on dense ground truth instead of sparse ground truthDDES · Indoor Flying split 1mean depth error (cm): 13.6 -> 16.7Hurt
train on dense ground truth instead of sparse ground truthDDES · Indoor Flying split 3mean depth error (cm): 18.4 -> 27.8Hurt
increase event queue capacity from 1 to 7 (shallow network) (ablation)shallow stereo network · Indoor Flying split 1 validationmean depth error (cm): 80.4 -> 67.9Improved
increase event queue capacity from 1 to 15 (deep network) (ablation)DDES · Indoor Flying split 1 validationmean depth error (cm): 13.3 -> 13.3No clear effect
increase event queue capacity from 1 to 7 (deep network) (ablation)DDES · Indoor Flying split 1 validationmean depth error (cm): 13.3 -> 13.5No 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