用普通彩色图像生成事件数据训练，让模型在无真实标注下也能泛化。
EventHub: Data Factory for Generalizable Event-Based Stereo Networks without Active Sensors
- 通过新视角合成技术从彩色图生成代理事件和标注
- 在多个事件立体数据集上实现超越现有方法的泛化能力
- 适合想低成本训练事件立体模型的研究者
我们提出 EventHub，一种无需昂贵主动传感器真值标注的深度事件立体网络训练框架，仅依赖标准彩色图像。通过先进新视角合成技术，从这些图像中生成代理标注与代理事件；若图像已配对事件数据，则仅需生成代理标注。利用该数据工厂构建的训练集，可复用现成的RGB立体模型处理事件数据，得到具备前所未有的泛化能力的事件立体模型。在广泛使用的事件立体数据集上的实验验证了 EventHub 的有效性，并表明相同的数据蒸馏机制可提升RGB立体基础模型在夜间等挑战性场景下的精度。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。