EventHub: Data Factory for Generalizable Event-Based Stereo Networks without Active Sensors
This provides a cost-effective solution for event-based stereo vision researchers by eliminating dependency on active sensors, though it builds incrementally on existing novel view synthesis and stereo model techniques.
The authors tackled the problem of training event-based stereo networks without expensive active sensor ground truth by creating EventHub, a framework that generates training data from standard color images using novel view synthesis. Their approach achieved unprecedented generalization capabilities for event stereo models and improved RGB stereo foundation model accuracy in challenging conditions like nighttime scenes.
We propose EventHub, a novel framework for training deep-event stereo networks without ground truth annotations from costly active sensors, relying instead on standard color images. From these images, we derive either proxy annotations and proxy events through state-of-the-art novel view synthesis techniques, or simply proxy annotations when images are already paired with event data. Using the training set generated by our data factory, we repurpose state-of-the-art stereo models from RGB literature to process event data, obtaining new event stereo models with unprecedented generalization capabilities. Experiments on widely used event stereo datasets support the effectiveness of EventHub and show how the same data distillation mechanism can improve the accuracy of RGB stereo foundation models in challenging conditions such as nighttime scenes.