论文标题
近乎近图片的3D时刻
3D Moments from Near-Duplicate Photos
论文作者
论文摘要
我们介绍了3D时刻，这是一种新的计算摄影效果。作为输入，我们拍摄了一对近乎简化的照片，即从类似观点移动主题的照片，在人们的照片集中常见。作为输出，我们制作了一个视频，该视频将场景运动从第一张照片到第二张的动作进行了平稳插值，同时还可以使用视差产生相机运动，从而增强了3D感。为了实现这种效果，我们将场景表示为一对基于特征的分层深度图像，并随着场景流的增强。此表示可以使运动插值以及对摄像机观点的独立控制。我们的系统通过运动视差和场景动态制作了影像现实主义的时空视频，同时恢复了原始视图中遮挡的区域。我们进行了广泛的实验，证明了公共数据集和野外照片上的基线优于基线。项目页面：https：//3d-moments.github.io/
We introduce 3D Moments, a new computational photography effect. As input we take a pair of near-duplicate photos, i.e., photos of moving subjects from similar viewpoints, common in people's photo collections. As output, we produce a video that smoothly interpolates the scene motion from the first photo to the second, while also producing camera motion with parallax that gives a heightened sense of 3D. To achieve this effect, we represent the scene as a pair of feature-based layered depth images augmented with scene flow. This representation enables motion interpolation along with independent control of the camera viewpoint. Our system produces photorealistic space-time videos with motion parallax and scene dynamics, while plausibly recovering regions occluded in the original views. We conduct extensive experiments demonstrating superior performance over baselines on public datasets and in-the-wild photos. Project page: https://3d-moments.github.io/
