EventHub:无需主动传感器的可泛化事件立体网络数据工厂
EventHub: Data Factory for Generalizable Event-Based Stereo Networks without Active Sensors
利用新视角合成从普通彩色图像生成代理标注和代理事件,从而无需主动传感器即可训练事件立体网络,这种数据工厂思路可迁移到其他缺乏真值的传感器模态(如事件光流、事件深度)。
原文依据 we derive either proxy annotations and proxy events through state-of-the-art novel view synthesis techniques
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论我们提出 EventHub,一种新颖的框架,用于训练深度事件立体网络,无需来自昂贵主动传感器的真值标注,而是依赖标准彩色图像。从这些图像中,我们通过最优的新视角合成技术推导出代理标注和代理事件,或者当图像已与事件数据配对时,仅推导代理标注。利用我们的数据工厂生成的训练集,我们重新利用 RGB 文献中的最优立体模型来处理事件数据,获得具有前所未有的泛化能力的新事件立体模型。在广泛使用的事件立体数据集上的实验支持了 EventHub 的有效性,并展示了相同的数据蒸馏机制如何提高 RGB 立体基础模型在夜间场景等挑战性条件下的精度。
英文原文摘要 854 字符
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.