当前位置: X-MOL 学术arXiv.cs.PF › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
GPU-Accelerated Mobile Multi-view Style Transfer
arXiv - CS - Performance Pub Date : 2020-03-02 , DOI: arxiv-2003.00706
Puneet Kohli, Saravana Gunaseelan, Jason Orozco, Yiwen Hua, Edward Li, and Nicolas Dahlquist

An estimated 60% of smartphones sold in 2018 were equipped with multiple rear cameras, enabling a wide variety of 3D-enabled applications such as 3D Photos. The success of 3D Photo platforms (Facebook 3D Photo, Holopix, etc) depend on a steady influx of user generated content. These platforms must provide simple image manipulation tools to facilitate content creation, akin to traditional photo platforms. Artistic neural style transfer, propelled by recent advancements in GPU technology, is one such tool for enhancing traditional photos. However, naively extrapolating single-view neural style transfer to the multi-view scenario produces visually inconsistent results and is prohibitively slow on mobile devices. We present a GPU-accelerated multi-view style transfer pipeline which enforces style consistency between views with on-demand performance on mobile platforms. Our pipeline is modular and creates high quality depth and parallax effects from a stereoscopic image pair.

中文翻译:

GPU 加速的移动多视图风格转移

据估计,2018 年售出的智能手机中有 60% 配备了多个后置摄像头,从而支持各种支持 3D 的应用程序,例如 3D 照片。3D 照片平台(Facebook 3D 照片、Holopix 等)的成功取决于用户生成内容的稳定涌入。这些平台必须提供简单的图像处理工具来促进内容创建,类似于传统的照片平台。由 GPU 技术的最新进展推动的艺术神经风格迁移就是一种用于增强传统照片的工具。然而,天真地将单视图神经风格转移外推到多视图场景会产生视觉上不一致的结果,并且在移动设备上速度非常慢。我们提出了一个 GPU 加速的多视图样式传输管道,它在移动平台上具有按需性能的视图之间强制执行样式一致性。我们的管道是模块化的,可以从立体图像对中创建高质量的深度和视差效果。
更新日期:2020-03-03
down
wechat
bug