提出一种兼顾效率与效果的物体放置方法
Hybrid Generative-Discriminative Object Placement
- 在背景上均匀设置锚点，融合前景与背景特征
- 通过评分筛选合理锚点并生成合理放置位置集合
- 在OPA数据集上实现效率与效果的平衡
物体放置是图像合成中的关键操作，旨在预测插入前景物体的合理位置和尺度。现有方法分为生成式与判别式两类，均难以兼顾效率与效果。本文提出一种介于两者之间的半生成式方法：在背景上均匀分布锚点，融合前景与背景特征，预测每个锚点的合理性得分，并为正锚点生成合理的放置位置集合。在OPA数据集上的大量实验表明，该方法能有效平衡效率与效果。
原文摘要 · Abstract (English)
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.
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。