Learn to See by Events: Color Frame Synthesis from Event and RGB Cameras
This work addresses the limited applicability of traditional vision algorithms for event cameras, enabling better integration into computer vision systems.
The paper tackles the problem of synthesizing RGB frames from event camera data by using an initial or periodic set of color key-frames and intermediate events, achieving high-quality results as confirmed by qualitative and quantitative evaluations on four public datasets.
Event cameras are biologically-inspired sensors that gather the temporal evolution of the scene. They capture pixel-wise brightness variations and output a corresponding stream of asynchronous events. Despite having multiple advantages with respect to traditional cameras, their use is partially prevented by the limited applicability of traditional data processing and vision algorithms. To this aim, we present a framework which exploits the output stream of event cameras to synthesize RGB frames, relying on an initial or a periodic set of color key-frames and the sequence of intermediate events. Differently from existing work, we propose a deep learning-based frame synthesis method, consisting of an adversarial architecture combined with a recurrent module. Qualitative results and quantitative per-pixel, perceptual, and semantic evaluation on four public datasets confirm the quality of the synthesized images.