Towards Anytime Optical Flow Estimation with Event Cameras

Yaozu Ye, Hao Shi, Kailun Yang, Ze Wang, Xiaoting Yin +3 more
7/11/2023
cs.CVcs.ROeess.IV

Official code: Yaozhuwa/EVA-Flow (18 stars, last commit 2024-09-19).

Abstract

Event cameras respond to changes in log-brightness at the millisecond level, making them ideal for optical flow estimation. However, existing datasets from event cameras provide only low frame rate ground truth for optical flow, limiting the research potential of event-driven optical flow. To address this challenge, we introduce a low-latency event representation, Unified Voxel Grid, and propose EVA-Flow, an EVent-based Anytime Flow estimation network to produce high-frame-rate event optical flow with only low-frame-rate optical flow ground truth for supervision. Furthermore, we propose the Rectified Flow Warp Loss (RFWL) for the unsupervised assessment of intermediate optical flow. A comprehensive variety of experiments on MVSEC, DESC, and our EVA-FlowSet demonstrates that EVA-Flow achieves competitive performance, super-low-latency (5ms), time-dense motion estimation (200Hz), and strong generalization. Our code will be available at https://github.com/Yaozhuwa/EVA-Flow.

View on arXivView PDF

Code Implementations(1)

Yaozhuwa/EVA-FlowOfficial100%

The official implementation code repository for EVA-Flow.

183PythonJul 11, 20232 years ago

Similar Papers

Secrets of Event-Based Optical Flow

91% match1 repo1972022

TMA: Temporal Motion Aggregation for Event-based Optical Flow

90% match1 repo332026

BlinkFlow: A Dataset to Push the Limits of Event-based Optical Flow Estimation

90% match2 repos222023

Graph Neural Network Combining Event Stream and Periodic Aggregation for Low-Latency Event-Based Vision

90% match2026

BAT: Learning Event-based Optical Flow with Bidirectional Adaptive Temporal Correlation

88% match2025

Tangentially Elongated Gaussian Belief Propagation for Event-Based Incremental Optical Flow Estimation

88% match2026

Cite this paper

@article{ye2023towards,
  title  = {Towards Anytime Optical Flow Estimation with Event Cameras},
  author = {Yaozu Ye and Hao Shi and Kailun Yang and Ze Wang and Xiaoting Yin and Lei Sun and Yaonan Wang and Kaiwei Wang},
  year   = {2023},
  eprint = {2307.05033},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2307.05033v3}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2307.05033.svg)](https://codeofpaper.com/paper/2307.05033)

Discussion