FoveaNet：视角感知的城市场景解析
FoveaNet: Perspective-aware Urban Scene Parsing
摘要：
解析城市场景图像有利于许多应用，特别是自动驾驶。目前大多数解决方案采用通用的图像解析模型，平等地对待图像中的所有尺度和位置，而不考虑汽车捕获的城市场景图像的几何属性。因此，他们遭受异构的对象规模所造成的透视投影的相机在实际场景中，不可避免地遇到解析失败的遥远的对象，以及其他边界和识别错误。在这项工作中，我们提出了一个新的FoveaNet模型，以充分利用场景图像的透视几何，并解决通用解析模型的常见故障。FoveaNet通过卷积网络估计场景图像的透视几何形状，该卷积网络集成了来自图像内上下文对象的支持性证据。基于透视几何信息，FoveaNet“撤消”相机透视投影分析区域在实际场景的空间中，从而提供更可靠的解析结果。此外，为了有效地解决识别错误，FoveaNet引入了一种新的密集CRF模型，该模型将透视几何作为先验势。我们在两个城市场景解析数据集Cityspaces和CamVid上评估了FoveaNet，这表明FoveaNet可以超越所有成熟的基线，并提供新的最先进的性能。
英文摘要：
Parsing urban scene images benefits many applications, especially self-driving. Most of the current solutions employ generic image parsing models that treat all scales and locations in the images equally and do not consider the geometry property of car-captured urban scene images. Thus, they suffer from heterogeneous object scales caused by perspective projection of cameras on actual scenes and inevitably encounter parsing failures on distant objects as well as other boundary and recognition errors. In this work, we propose a new FoveaNet model to fully exploit the perspective geometry of scene images and address the common failures of generic parsing models. FoveaNet estimates the perspective geometry of a scene image through a convolutional network which integrates supportive evidence from contextual objects within the image. Based on the perspective geometry information, FoveaNet "undoes" the camera perspective projection analyzing regions in the space of the actual scene, and thus provides much more reliable parsing results. Furthermore, to effectively address the recognition errors, FoveaNet introduces a new dense CRFs model that takes the perspective geometry as a prior potential. We evaluate FoveaNet on two urban scene parsing datasets, Cityspaces and CamVid, which demonstrates that FoveaNet can outperform all the well-established baselines and provide new state-of-the-art performance.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
