TL;DR
This paper introduces a novel framework to convert binocular videos into monocular videos with implicit stereo information, enabling easy distribution and high-quality restoration of the original 3D content on stereoscopic displays.
Contribution
We propose a self-supervised encoding-decoding framework with specialized modules to effectively mononize binocular videos and restore the original stereo content, addressing artifact suppression and noise resilience.
Findings
High-quality mononized videos with preserved stereo information
Effective restoration of original binocular videos from mononized versions
Positive user perception and quantitative metrics confirming method effectiveness
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
