arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2101.04626cs.CVcs.AI
收藏

从语义特征预测对象间的相对深度

Predicting Relative Depth between Objects from Semantic Features

University of Malta(马耳他大学)

Stefan Cassar, Adrian Muscat, Dylan Seychell

摘要:

视觉和语言任务,如视觉关系检测和视觉问答受益于语义特征,提供适当的语言基础。在2D图像中描绘的对象的3D深度是这样的特征之一。然而,它是非常困难的,以获得准确的深度信息,而不学习适当的功能,这是场景相关的。该领域的现有技术是在立体图像数据上训练的复杂神经网络模型,以预测每个像素的深度。幸运的是,在某些任务中,只需要对象之间的相对深度。本文研究了语义特征在多大程度上可以预测课程相对深度。该问题被视为一个分类问题,基于对象边界框、对象标签和场景属性的几何特征被计算并用作模式识别模型的输入,以预测相对深度。即在后、在前和中立。结果进行比较,从平均的monodepth神经网络模型,这代表了国家的最先进的输出。相对于从monodepth模型得出的结果计算的相对深度的相对深度精度的总体增加14%。

英文摘要:

Vision and language tasks such as Visual Relation Detection and Visual Question Answering benefit from semantic features that afford proper grounding of language. The 3D depth of objects depicted in 2D images is one such feature. However it is very difficult to obtain accurate depth information without learning the appropriate features, which are scene dependent. The state of the art in this area are complex Neural Network models trained on stereo image data to predict depth per pixel. Fortunately, in some tasks, its only the relative depth between objects that is required. In this paper the extent to which semantic features can predict course relative depth is investigated. The problem is casted as a classification one and geometrical features based on object bounding boxes, object labels and scene attributes are computed and used as inputs to pattern recognition models to predict relative depth. i.e behind, in-front and neutral. The results are compared to those obtained from averaging the output of the monodepth neural network model, which represents the state-of-the art. An overall increase of 14% in relative depth accuracy over relative depth computed from the monodepth model derived results is achieved.

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。

↑