This paper presents the idea ofmono-nizingbinocular videos and a frame-work
to effectively realize it. Mono-nize means we purposely convert abinocular
video into a regular monocular video with the stereo informationimplicitly
encoded in a visual but nearly-imperceptible form. Hence, wecan impartially
distribute and show the mononized video as an ordinarymonocular video. Unlike
ordinary monocular videos, we can restore from itthe original binocular video
and show it on a stereoscopic display. To start,we formulate an
encoding-and-decoding framework with the pyramidal de-formable fusion module to
exploit long-range correspondences between theleft and right views, a
quantization layer to suppress the restoring artifacts,and the compression
noise simulation module to resist the compressionnoise introduced by modern
video codecs. Our framework is self-supervised,as we articulate our objective
function with loss terms defined on the input:a monocular term for creating the
mononized video, an invertibility termfor restoring the original video, and a
temporal term for frame-to-framecoherence. Further, we conducted extensive
experiments to evaluate ourgenerated mononized videos and restored binocular
videos for diverse typesof images and 3D movies. Quantitative results on both
standard metrics anduser perception studies show the effectiveness of our
method.

该论文提出了将双目视频转换为单目视频的概念，并介绍了一个编码解码框架来有效实现它。该框架是自监督的，以损失项定义目标函数，并通过大量实验证明了该方法的有效性。

双目视频单目化

Mononizing Binocular Videos

With the mass-market adoption of dual-camera mobile phones, leveraging stereo
information in computer vision has become increasingly important. Current
state-of-the-art methods utilize learning-based algorithms, where the amount
and quality of training samples heavily influence results. Existing stereo
image datasets are limited either in size or subject variety. Hence, algorithms
trained on such datasets do not generalize well to scenarios encountered in
mobile photography. We present Holopix50k, a novel in-the-wild stereo image
dataset, comprising 49,368 image pairs contributed by users of the Holopix
mobile social platform. In this work, we describe our data collection process
and statistically compare our dataset to other popular stereo datasets. We
experimentally show that using our dataset significantly improves results for
tasks such as stereo super-resolution and self-supervised monocular depth
estimation. Finally, we showcase practical applications of our dataset to
motivate novel works and use cases. The Holopix50k dataset is available at
this http URL

本文描述了 Holopix50k 这一在野外采集的新型立体图像数据集，用于训练改进移动摄影场景下的立体超分辨率和无监督单目深度估计算法，并展示了该数据集的实际应用以激励新的作品和用例。