Back to Event Basics: Self-Supervised Learning of Image Reconstruction for Event Cameras via Photometric Constancy
This work addresses the gap between event-based and frame-based computer vision for researchers and practitioners, though it is incremental as it builds on existing reconstruction efforts.
The paper tackles the problem of reconstructing intensity frames from event camera data by introducing a self-supervised learning method that uses optical flow and photometric constancy, achieving performance in line with state-of-the-art across multiple datasets.
Event cameras are novel vision sensors that sample, in an asynchronous fashion, brightness increments with low latency and high temporal resolution. The resulting streams of events are of high value by themselves, especially for high speed motion estimation. However, a growing body of work has also focused on the reconstruction of intensity frames from the events, as this allows bridging the gap with the existing literature on appearance- and frame-based computer vision. Recent work has mostly approached this problem using neural networks trained with synthetic, ground-truth data. In this work we approach, for the first time, the intensity reconstruction problem from a self-supervised learning perspective. Our method, which leverages the knowledge of the inner workings of event cameras, combines estimated optical flow and the event-based photometric constancy to train neural networks without the need for any ground-truth or synthetic data. Results across multiple datasets show that the performance of the proposed self-supervised approach is in line with the state-of-the-art. Additionally, we propose a novel, lightweight neural network for optical flow estimation that achieves high speed inference with only a minor drop in performance.