Computer Vision - ECCV 2022 - 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part XXIII
Computer Vision - ECCV 2022 - 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part XXIII
复制标题
计算机视觉 - ECCV 2022 - 第 17 届欧洲会议，以色列特拉维夫，2022 年 10 月 23-27 日，会议记录，第 XXIII 部分
DOI：
10.1007/978-3-031-20050-2_15
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Sheng Y
中科院分区：
文献类型：
--
作者：
Sheng Y
阴影对于从2D图像剪切合成逼真的图像至关重要。基于物理的阴影渲染方法需要3D几何图形，但这并不总是可用的。基于深度学习的阴影合成方法学习从光线信息到对象阴影的映射，而无需显式地对阴影几何体进行建模。尽管如此，他们缺乏控制，容易出现视觉伪影。我们引入“像素高度”，一种新的几何表示，编码对象，地面和相机姿态之间的相关性。像素高度可以从3D几何图形计算，在2D图像上手动注释，也可以通过监督方法从单视图RGB图像预测。它可用于基于投影几何计算2D图像中的硬阴影，提供对阴影方向和形状的精确控制。此外，我们提出了一个数据驱动的软阴影生成器应用软的硬阴影的基础上的软输入参数。定性和定量的评价表明，建议的像素高度显着提高了阴影生成的质量，同时允许可控性。
Shadows are essential for realistic image compositing from 2D image cutouts. Physics-based shadow rendering methods require 3D geometries, which are not always available. Deep learning-based shadow synthesis methods learn a mapping from the light information to an object’s shadow without explicitly modeling the shadow geometry. Still, they lack control and are prone to visual artifacts. We introduce “Pixel Height", a novel geometry representation that encodes the correlations between objects, ground, and camera pose. The Pixel Height can be calculated from 3D geometries, manually annotated on 2D images, and can also be predicted from a single-view RGB image by a supervised approach. It can be used to calculate hard shadows in a 2D image based on the projective geometry, providing precise control of the shadows’ direction and shape. Furthermore, we propose a data-driven soft shadow generator to apply softness to a hard shadow based on a softness input parameter. Qualitative and quantitative evaluations demonstrate that the proposed Pixel Height significantly improves the quality of the shadow generation while allowing for controllability.