This work aims to provide a deep-learning solution for the motion
interpolation task. Previous studies solve it with geometric weight functions.
Some other works propose neural networks for different problem settings with
consecutive pose sequences as input. However, motion interpolation is a more
complex problem that takes isolated poses (e.g., only one start pose and one
end pose) as input. When applied to motion interpolation, these deep learning
methods have limited performance since they do not leverage the flexible
dependencies between interpolation frames as the original geometric formulas
do. To realize this interpolation characteristic, we propose a novel framework,
referred to as \emph{Shuffled AutoRegression}, which expands the autoregression
to generate in arbitrary (shuffled) order and models any inter-frame
dependencies as a directed acyclic graph. We further propose an approach to
constructing a particular kind of dependency graph, with three stages assembled
into an end-to-end spatial-temporal motion Transformer. Experimental results on
one of the current largest datasets show that our model generates vivid and
coherent motions from only one start frame to one end frame and outperforms
competing methods by a large margin. The proposed model is also extensible to
multiple keyframes' motion interpolation tasks and other areas' interpolation.

提出了一种名为 “Shuffled AutoRegression” 的新框架，扩展了自回归以生成任意（洗牌）顺序并将任何帧之间的依赖关系建模为有向无环图，并提出了一种方法来构建特定类型的依赖图，该模型在单个起始帧到单个结束帧的插值任务和其他领域的插值中都表现出色。

动作插值的随机自回归

Shuffled Autoregression For Motion Interpolation

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: this https URL

本文提出了 3D Moments，一种基于计算摄影的新效果，利用特征匹配的一对近似重复照片，将场景转换为具有空间深度的视频，可以实现照片间的模糊过渡效果，摄像机视角的改变和物体在场景中的移动，能够逼真地恢复遮挡区域，提供了一种突出 3D 感觉的视觉效果。

从近似重复的照片中提取 3D 矩

3D Moments from Near-Duplicate Photos

We propose a novel approach for 3D video synthesis that is able to represent
multi-view video recordings of a dynamic real-world scene in a compact, yet
expressive representation that enables high-quality view synthesis and motion
interpolation. Our approach takes the high quality and compactness of static
neural radiance fields in a new direction: to a model-free, dynamic setting. At
the core of our approach is a novel time-conditioned neural radiance field that
represents scene dynamics using a set of compact latent codes. We are able to
significantly boost the training speed and perceptual quality of the generated
imagery by a novel hierarchical training scheme in combination with ray
importance sampling. Our learned representation is highly compact and able to
represent a 10 second 30 FPS multiview video recording by 18 cameras with a
model size of only 28MB. We demonstrate that our method can render
high-fidelity wide-angle novel views at over 1K resolution, even for complex
and dynamic scenes. We perform an extensive qualitative and quantitative
evaluation that shows that our approach outperforms the state of the art.
Project website: this https URL

提出了一种新的 3D 视频合成方法，使用神经辐射场表示动态实景，并使用一种紧凑的表现方式，能够高质量地合成视图和插值运动，其动态场景建模方法在视角合成和动态场景表示方面都表现良好。