AI Paper Atlas

Research map / Video / Video generation

Texvent: Asynchronous Event Data Simulation via Text Prompt

Ruofei Wang, Peiqi Duan, Ka Chun Cheung, Simon See, Boxin Shi, Renjie Wan

CVPR 2026 · Video › Video generation · approach: Compositional text-to-video diffusion

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 balancing parameter alpha to the log intensity comparison (ablation)Texvent · NT-ImageNet (single example)EQS: 0.8309 -> 0.8474Improved
add brightness cache for voltage refreshment (ablation)Texvent · NT-ImageNet (single example)EQS: 0.8073 -> 0.8474 (4.01% drop without cache)Improved
augment training data with 5% Texvent eventsHyperE2VID · Event Camera Dataset reconstructionPSNR: 21.9488 -> 23.3000Improved
augment training data with 5% Texvent eventsE2VID · Event Camera Dataset reconstructionPSNR: 22.1127 -> 22.8475Improved
augment training data with 5% Texvent eventsETNet · Event Camera Dataset reconstructionLPIPS: 0.2013 -> 0.2112Hurt
augment training data with 5% Texvent eventsETNet · Event Camera Dataset reconstructionPSNR: 21.1987 -> 21.3771Improved
use brightness-aware interpolation instead of optical-flow-based interpolation (Texvent vs VID2E/V2E)Texvent · NT-ImageNetTime (s): 2.1228 -> 0.0653Improved

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