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/
翻译:作为输入,我们拍摄了一副近似复制的照片,即从类似角度移动主题的照片,这是人们照片收藏中常见的。作为输出,我们制作了一段视频,将现场运动从第一张照片顺利地从第一张照片插入第二张,同时用配有3D感的配方轴制作摄影机动作,使3D感触觉更加强烈。为了达到这一效果,我们将场景代表成一副基于地貌的层层深度图像,与场景流相增强。通过这种演示,可以对摄像器视图进行运动的相互调和独立控制。我们的系统制作了带有移动伞和场景动态的摄影现实空间时段视频,同时在原始视图中可以令人信服地恢复区域。我们进行了广泛的实验,展示了优于公共数据集基线和网络照片的优异性表现。项目网页:https://3d-moments.github.io/