混合生成-判别式物体放置

中文摘要 AI 辅助

作为图像合成的重要操作，物体放置旨在为插入的前景物体预测合理的放置位置（位置、尺度）。现有的物体放置方法可分为生成式方法和判别式方法，两者均无法很好地平衡效率与效果。在本研究中，我们提出一种介于两者之间的半生成式方法。具体而言，我们在背景上分配均匀分布的锚点，随后融合前景与背景特征以预测每个锚点的合理性得分，并为正锚点预测合理的放置集合。在OPA数据集上开展的大量实验表明，我们的方法能够在效率与效果之间取得良好平衡。

英文摘要

As an important operation of image composition, object placement aims to predict the plausible placement (location, scale) for the inserted foreground object. Previous object placement methods can be divided into generative methods and discriminative methods, both of which cannot balance efficiency and effectiveness well. In this work, we propose a semi-generative method in the middle ground between them. In particular, we assign uniformly distributed anchors on the background. Then, we fuse foreground and background features to predict the rationality score for each anchor and predict plausible placement sets for positive anchors. Extensive experiments on the OPA dataset show that our method can strike a good balance between efficiency and effectiveness.

发表机构

• Shanghai Jiao Tong University（上海交通大学）

机构由 AI 辅助整理，请以论文原文为准。