论文标题
无限性质：从单个图像中的自然场景的永久视图产生
Infinite Nature: Perpetual View Generation of Natural Scenes from a Single Image
论文作者
论文摘要
我们介绍了永久视图生成的问题 - 远程生成的新视图对应于单个图像的任意长相机轨迹。这是一个具有挑战性的问题，它远远超出了当前视图合成方法的能力，该方法在出现大型摄像机运动时迅速退化。视频生成的方法还具有有限的产生长序列的能力，并且通常对场景几何形状不可知。我们采用一种混合方法，该方法将几何和图像合成集成在迭代`\ emph {render}，\ emph {prifine}和\ emph {repot}'框架中，从而允许远距离生成数百帧后覆盖大距离。我们的方法可以通过一组单眼视频序列进行训练。我们提出了沿海场景的航空镜头数据集，并将我们的方法与最近的视图合成和有条件的视频生成基线进行比较，表明它可以在大型摄像机轨迹上与现有方法相比，在更长的时间范围内生成可行的场景。 https://infinite-nature.github.io/的项目页面。
We introduce the problem of perpetual view generation - long-range generation of novel views corresponding to an arbitrarily long camera trajectory given a single image. This is a challenging problem that goes far beyond the capabilities of current view synthesis methods, which quickly degenerate when presented with large camera motions. Methods for video generation also have limited ability to produce long sequences and are often agnostic to scene geometry. We take a hybrid approach that integrates both geometry and image synthesis in an iterative `\emph{render}, \emph{refine} and \emph{repeat}' framework, allowing for long-range generation that cover large distances after hundreds of frames. Our approach can be trained from a set of monocular video sequences. We propose a dataset of aerial footage of coastal scenes, and compare our method with recent view synthesis and conditional video generation baselines, showing that it can generate plausible scenes for much longer time horizons over large camera trajectories compared to existing methods. Project page at https://infinite-nature.github.io/.
