Enhanced Frame and Event-Based Simulator and Event-Based Video Interpolation Network
This work addresses the challenge of improving video interpolation for applications requiring high frame rates, though it appears incremental with enhancements to simulation and model design.
The paper tackles the problem of high-quality video interpolation by combining neuromorphic event-based sensors with conventional frame-based sensors, resulting in reconstructed images on public datasets that are equivalent or better than state-of-the-art quality.
Fast neuromorphic event-based vision sensors (Dynamic Vision Sensor, DVS) can be combined with slower conventional frame-based sensors to enable higher-quality inter-frame interpolation than traditional methods relying on fixed motion approximations using e.g. optical flow. In this work we present a new, advanced event simulator that can produce realistic scenes recorded by a camera rig with an arbitrary number of sensors located at fixed offsets. It includes a new configurable frame-based image sensor model with realistic image quality reduction effects, and an extended DVS model with more accurate characteristics. We use our simulator to train a novel reconstruction model designed for end-to-end reconstruction of high-fps video. Unlike previously published methods, our method does not require the frame and DVS cameras to have the same optics, positions, or camera resolutions. It is also not limited to objects a fixed distance from the sensor. We show that data generated by our simulator can be used to train our new model, leading to reconstructed images on public datasets of equivalent or better quality than the state of the art. We also show our sensor generalizing to data recorded by real sensors.