FlowFeat: Pixel-Dense Embedding of Motion Profiles

NeurIPSSpotlight2025

Authors: Nikita Araslanov, Anna Ribic, Daniel Cremers
Venue: NeurIPS 2025
Track: Spotlight

TL;DR

Dense and versatile image representations underpin the success of virtually all computer vision applications…

Opening excerpt from the authors’ abstract. source

Read the paper

OpenReview

Topics

computer vision

← All NeurIPS 2025 Spotlight papers · Browse the whole archive