Simultaneous Optical Flow and Intensity Estimation from an Event Camera

By Patrick Bardow, Andrew J. Davison, Stefan Leutenegger. Computer Vision and Pattern Recognition, 2016

329 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/c04c7d4abc5f0774b2dfd4e44ed183630da53e38

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

In Electrical and Electronic Engineering

Citations in the corpus

EV-FlowNet: Self-Supervised Optical Flow Estimation for Event-based Cameras (2018, methodology): “In our experiments, k ∈ [2 , 4 , 6 , 8 , 10 , 12] .”
Learning to Detect Objects with a 1 Megapixel Event Camera (2020, background): “To overcome these limitations, several works have focused on the reconstruction of gray-level information from an event stream [7, 8, 9, 10].”
End-to-End Learning of Representations for Asynchronous Event-Based Data (2019, background): “Low-level applications include optical flow prediction [8, 9] and image reconstruction [5].”
The event-camera dataset and simulator: Event-based data for pose estimation, visual odometry, and SLAM (2016, background): “…2D (Weikersdorfer et al. 2013) and 3D (Kueng et al. 2016; Kim et al. 2016; Rebecq et al. 2016b), optical ﬂow (Cook et al. 2011; Benosman et al. 2014; Bardow et al. 2016), visual odometry (Censi and Scaramuzza 2014), 6-DOF localization for high-speed robotics (Mueggler et al. 2014), line detection…”
Events-To-Video: Bringing Modern Computer Vision to Event Cameras (2019, methodology): “Our work differs from previous image reconstruction approaches [3, 31, 43] in two essential ways.”
High Speed and High Dynamic Range Video with an Event Camera (2019, methodology): “Qualitative comparison on the dataset introduced by [2].”
Real-Time 3D Reconstruction and 6-DoF Tracking with an Event Camera (2016, methodology): “[1] presented an optical flow and intensity estimation using an event camera which allows any camera motion as well as dynamic scenes.”
Unsupervised Event-Based Learning of Optical Flow, Depth, and Egomotion (2018, background): “[1] show that flow estimation can be written as a convex optimization problem that solves for the image intensity and flow jointly.”
Event-Based Vision: A Survey (2019, methodology): “In these methods voxel grids are used as an internal representation [112] (e.”
Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age (2016, unknown): “n 100 papers on the algorithmic use of these sensors. Event-based adaptations of feature detection and tracking [72, 181], epipolar geometry [23], image reconstruction, motion estimation, optical ﬂow [17, 22, 76, 168], 3D reconstruction [56, 260] visual odometry [65, 260], localization [216, 217, 32”
A Unifying Contrast Maximization Framework for Event Cameras, with Applications to Motion, Depth, and Optical Flow Estimation (2018, methodology): “This category can be further subdivided into two: 2a)methods that discard temporal information of the events and accumulate them into frames to re-utilize traditional, image-based computer vision algorithms [16, 17, 18], and 2b) methods that exploit the temporal information of the events during the ”
Bringing a Blurry Frame Alive at High Frame-Rate With an Event Camera (2018, methodology): “The existing methods can be in general categorized as 1) Event data only solutions [1, 27, 2], where the results tend to lack the texture and consistency of natural videos, as they fail to use the complementary information contained in the low frame-rate intensity image; 2) Low framerate intensity-i”