AI Paper Atlas

Research map / Video / Video segmentation and tracking

Event based Multi-Velocity-Scale Imaging

Qiyao Gao, Peiqi Duan, Chu Zhou, Xinyu Zhou, Imari Sato, Boxin Shi

NeurIPS 2026 · Video › Video segmentation and tracking · approach: Event-based video reconstruction

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes event-based imaging that handles static, slow, and fast motion within one scene, motivated by the limits of frame cameras and single-threshold event sensors.

Problem

Frame cameras oversample slow and static regions when imaging scenes with mixed velocities, and standard event cameras use a single global contrast threshold that trades off sensitivity against dynamic range or noise for different motion speeds.

Approach

Abstract is truncated; the stated motivation is asynchronous local sensing adapted to multiple velocity scales within one field of view, rather than a single global contrast threshold. The specific mechanism is not stated in the provided text.

Limitations

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