Injecting Frame-Event Complementary Fusion into Diffusion for Optical Flow in Challenging Scenes

NeurIPSSpotlight2025

Authors
Haonan Wang, Hanyu Zhou, Haoyue Liu, Luxin Yan
Venue
NeurIPS 2025
Track
Spotlight

TL;DR

Optical flow estimation has achieved promising results in conventional scenes but faces challenges in high-speed and low-light scenes, which suffer from motion blur and insufficient illumination…

Opening excerpt from the authors’ abstract. source

Read the paper

Topics

diffusion

← All NeurIPS 2025 Spotlight papers · Browse the whole archive