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 2205.14280cs.CV
收藏

快速对象放置评估

Fast Object Placement Assessment

Shanghai Jiao Tong University(上海交通大学);Beijing Institute of Technology(北京理工大学)

Li Niu, Qingyang Liu, Zhenchen Liu, Jiangtong Li

摘要:

对象放置评估(OPA)旨在根据放置来预测合成图像的合理性分数(例如,比例、位置)。然而,给定一对缩放的前景和背景,现有的OPA模型需要将前景放置在背景上的每个位置,并将获得的合成图像一次一个地通过模型,这是非常耗时的。在这项工作中,我们研究了一个新的任务命名为快速OPA。具体来说,提供缩放的前景和背景,我们只将它们通过模型一次,并预测所有位置的合理性得分。为了完成这一任务,我们提出了一个开创性的快速OPA模型与几个创新(即,前景动态滤波器、背景先验转移和复合特征模仿),以弥合慢速OPA模型和快速OPA模型之间的性能差距。在OPA数据集上的大量实验表明,我们提出的快速OPA模型与慢速OPA模型的性能相当,但运行速度明显更快。

英文摘要:

Object placement assessment (OPA) aims to predict the rationality score of a composite image in terms of the placement (e.g., scale, location) of inserted foreground object. However, given a pair of scaled foreground and background, to enumerate all the reasonable locations, existing OPA model needs to place the foreground at each location on the background and pass the obtained composite image through the model one at a time, which is very time-consuming. In this work, we investigate a new task named as fast OPA. Specifically, provided with a scaled foreground and a background, we only pass them through the model once and predict the rationality scores for all locations. To accomplish this task, we propose a pioneering fast OPA model with several innovations (i.e., foreground dynamic filter, background prior transfer, and composite feature mimicking) to bridge the performance gap between slow OPA model and fast OPA model. Extensive experiments on OPA dataset show that our proposed fast OPA model performs on par with slow OPA model but runs significantly faster.

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。

↑