论文标题
流离失所：室外单图像重新照顾铸造阴影
OutCast: Outdoor Single-image Relighting with Cast Shadows
论文作者
论文摘要
我们提出了一种用于户外图像的重新方法。我们的方法主要集中于从单个图像中预测任意新颖的照明方向上的铸造阴影，同时还考虑了阴影和全球效果，例如太阳浅色和云。此问题的先前解决方案依赖于重建封闭器的几何形状，例如使用多视图立体声，它需要场景的许多图像。取而代之的是，在这项工作中，我们利用嘈杂的现成的单像深度图估计作为几何形状来源。尽管这可能是一些照明效果的好指南，但所得的深度图质量不足以直接射线追踪阴影。在解决这个问题时，我们提出了一个学习的图像空间射线建筑层，该图层将近似深度映射转换为深3D表示，并使用学习的遍历将其融合到遮挡查询中。我们提出的方法首次实现了最新的重新确认结果，只有一个图像作为输入。有关补充材料，请访问我们的项目页面：https：//dgriffiths.uk/outcast。
We propose a relighting method for outdoor images. Our method mainly focuses on predicting cast shadows in arbitrary novel lighting directions from a single image while also accounting for shading and global effects such the sun light color and clouds. Previous solutions for this problem rely on reconstructing occluder geometry, e.g. using multi-view stereo, which requires many images of the scene. Instead, in this work we make use of a noisy off-the-shelf single-image depth map estimation as a source of geometry. Whilst this can be a good guide for some lighting effects, the resulting depth map quality is insufficient for directly ray-tracing the shadows. Addressing this, we propose a learned image space ray-marching layer that converts the approximate depth map into a deep 3D representation that is fused into occlusion queries using a learned traversal. Our proposed method achieves, for the first time, state-of-the-art relighting results, with only a single image as input. For supplementary material visit our project page at: https://dgriffiths.uk/outcast.
