论文标题
自由视图合成
Free View Synthesis
论文作者
论文摘要
我们提出了一种从自由分布在场景周围的输入图像中的新型视图合成的方法。我们的方法不依赖于定期的输入视图安排，可以合成图像以通过场景的自由相机移动，并适用于具有不受约束的几何布局的一般场景。我们通过SFM校准输入图像，并通过MVS建立粗糙的几何支架。该脚手架用于创建代理深度图，以欣赏场景的新颖景色。基于此深度映射，一个经常性的编码器 - 码头网络进程从附近的视图中重新注射的功能并综合了新视图。我们的网络无需针对给定场景进行优化。在数据集上进行了培训后，它在以前看不见的环境中起作用，没有微调或每场现场优化。我们评估了有关挑战现实世界数据集（包括坦克和寺庙）的提出方法，在这里我们首次展示了成功的视图合成，并且在事先和同时进行的工作大大胜过。
We present a method for novel view synthesis from input images that are freely distributed around a scene. Our method does not rely on a regular arrangement of input views, can synthesize images for free camera movement through the scene, and works for general scenes with unconstrained geometric layouts. We calibrate the input images via SfM and erect a coarse geometric scaffold via MVS. This scaffold is used to create a proxy depth map for a novel view of the scene. Based on this depth map, a recurrent encoder-decoder network processes reprojected features from nearby views and synthesizes the new view. Our network does not need to be optimized for a given scene. After training on a dataset, it works in previously unseen environments with no fine-tuning or per-scene optimization. We evaluate the presented approach on challenging real-world datasets, including Tanks and Temples, where we demonstrate successful view synthesis for the first time and substantially outperform prior and concurrent work.
