The problem of predicting a novel view of the scene using an arbitrary number of observations is a challenging problem for computers as well as for humans. This paper introduces the Generative Adversarial Query Network (GAQN), a general learning framework for novel view synthesis that combines Generative Query Network (GQN) and Generative Adversarial Networks (GANs). The conventional GQN encodes input views into a latent representation that is used to generate a new view through a recurrent variational decoder. The proposed GAQN builds on this work by adding two novel aspects: First, we extend the current GQN architecture with an adversarial loss function for improving the visual quality and convergence speed. Second, we introduce a feature-matching loss function for stabilizing the training procedure. The experiments demonstrate that GAQN is able to produce high-quality results and faster convergence compared to the conventional approach.

中文翻译：

---

使用生成对抗查询网络预测新观点

使用任意数量的观察来预测场景的新视图对计算机和人类来说都是一个具有挑战性的问题。本文介绍了生成对抗查询网络 (GAQN)，这是一种结合了生成查询网络 (GQN) 和生成对抗网络 (GAN) 的新颖视图合成的通用学习框架。传统的 GQN 将输入视图编码为潜在表示，该表示用于通过循环变分解码器生成新视图。提议的 GAQN 通过添加两个新方面来建立在这项工作的基础上：首先，我们使用对抗性损失函数扩展当前的 GQN 架构，以提高视觉质量和收敛速度。其次，我们引入了一个特征匹配损失函数来稳定训练过程。