Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

computer-vision-9

Event-based Optical Flow

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in event-based-optical-flow-9

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

Use these libraries to find event-based-optical-flow-9 models and implementations

Datasets

DSEC

EKubric

Subtasks

No subtasks available.

Most implemented papers

Spike-FlowNet: Event-based Optical Flow Estimation with Energy-Efficient Hybrid Neural Networks

K. Roy, Kostas Daniilidis, A. Z. Zhu, Chankyu Lee, Adarsh Kosta, Kenneth Chaney•Fri Mar 13 2020

Spike-FlowNet is presented, a deep hybrid neural network architecture integrating SNNs and ANNs for efficiently estimating optical flow from sparse event camera outputs without sacrificing the performance.

188

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

Paper Graph

Spatio-Temporal Recurrent Networks for Event-Based Optical Flow Estimation

Zhaofei Yu, Tiejun Huang, Ziluo Ding, Rui Zhao, Jiyuan Zhang, Tianxiao Gao, Ruiqin Xiong•Thu Sep 09 2021

A spatio-temporal recurrent encoding-decoding neural network architecture for event-based optical flow estimation, which utilizes Convolutional Gated Recurrent Units to extract feature maps from a series of event images.

71 0

Paper Graph

Real-Time Optical Flow for Vehicular Perception With Low- and High-Resolution Event Cameras

F. Davoine, Vincent Brebion, Julien Moreau•Sun Dec 19 2021

This work proposes an optimized framework for computing optical flow in real-time with both low- and high-resolution event cameras, and formulate a novel dense representation for the sparse events flow, in the form of the “inverse exponential distance surface”.

46 0

Paper Graph

Secrets of Event-Based Optical Flow

Guillermo Gallego, Y. Aoki, Shintaro Shiba•Tue Jul 19 2022

A principled method to extend the Contrast Maximization framework to estimate optical flow from events alone, which ranks first among unsupervised methods on the MVSEC benchmark, and is competitive on the DSEC benchmark.

120 0

Paper Graph

Event-based Temporally Dense Optical Flow Estimation with Sequential Learning

Wachirawit Ponghiran, C. Liyanagedera, Kaushik Roy•Sun Oct 02 2022

This work shows that a temporally dense flow estimation at 100 Hz can be achieved by treating the flow estimation as a sequential problem using two different variants of recurrent networks – Long-short term memory (LSTM) and spiking neural network (SNN).

18 0

Paper Graph

TMA: Temporal Motion Aggregation for Event-based Optical Flow

Guang Chen, Alois Knoll, Changjun Jiang, Sanqing Qu, Zhijun Li, Yanping Zhang•Mon Mar 20 2023

By incorporating temporally fine-grained motion information, TMA can derive better flow estimates than existing methods at early stages, which not only enables TMA to obtain more accurate final predictions, but also greatly reduces the demand for a number of refinements.

41 0

Paper Graph

IDO-VFI: Identifying Dynamics via Optical Flow Guidance for Video Frame Interpolation with Events

Chenyang Shi, Hanxiao Liu, Jing Jin, Wenzhuo Li, Yuzhen Li, Boyi Wei, Yibo Zhang•Tue May 16 2023

This paper proposes an event-and-frame-based video frame interpolation method named IDO-VFI that assigns varying amounts of computation for different sub-regions via optical flow guidance and outperforms state-of-the-art frame-only and frames-plus-events methods on multiple videoframe interpolation benchmarks.

1 0

Paper Graph

Adding a benchmark result helps the community track progress.

Event-based Optical Flow | State-of-the-Art