AI Paper Atlas

Research map / Video / Video segmentation and tracking

Focus Is All You Need: Loss Functions for Event-Based Vision

Guillermo Gallego, Mathias Gehrig, Davide Scaramuzza

CVPR 2019 · Video › Video segmentation and tracking · approach: Event-based video reconstruction · 147 citations (OpenAlex)

Check 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 IWE gradient magnitude instead of the timestamp-based lossEvent-camera rotational motion compensation · boxes_rotationRMS angular velocity error (°/s): 82.89 -> 17.83Improved
Use IWE derivatives (gradient or Laplacian) rather than the variance baselineEvent-camera rotational motion compensation · boxes_rotationRMS angular velocity error (°/s): 18.52 -> 17.58Improved
Use event polarity (ablation)Focus-loss motion compensation · Boxes and PosterRMS angular velocity error (°/s): 18.52 -> 18.94; 25.96 -> 24.39Mixed
Use variance rather than gradient magnitudeFocus-loss motion compensation · Boxesruntime (µs): 128.46 -> 16.90Improved
Use timestamp-based alignment rather than event-count-based focus lossesEvent-camera rotational motion compensation · boxes_rotationRMS angular velocity error (°/s): 17.83 -> 82.89Hurt

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