论文标题
深360 $^\ circ $基于多预测融合的光流估计
Deep 360$^\circ$ Optical Flow Estimation Based on Multi-Projection Fusion
论文作者
论文摘要
在视频处理管道的早期阶段，光流计算至关重要。本文重点介绍了该领域较少探索的问题，即使用深层神经网络的360 $^\ circ $光流估算，以支持越来越流行的VR应用程序。为了解决应用卷积神经网络时全景表示的扭曲，我们提出了一个新型的多预测融合框架，该框架融合了使用使用不同投影方法训练的模型预测的光流。它学会了将互补信息结合在不同预测下的光流结果中。我们还构建了第一个大规模全景光流数据集，以支持神经网络的训练和全景光流估计方法的评估。我们数据集上的实验结果表明，我们的方法优于用于处理360°含量的现有方法和其他替代深层网络。
Optical flow computation is essential in the early stages of the video processing pipeline. This paper focuses on a less explored problem in this area, the 360$^\circ$ optical flow estimation using deep neural networks to support increasingly popular VR applications. To address the distortions of panoramic representations when applying convolutional neural networks, we propose a novel multi-projection fusion framework that fuses the optical flow predicted by the models trained using different projection methods. It learns to combine the complementary information in the optical flow results under different projections. We also build the first large-scale panoramic optical flow dataset to support the training of neural networks and the evaluation of panoramic optical flow estimation methods. The experimental results on our dataset demonstrate that our method outperforms the existing methods and other alternative deep networks that were developed for processing 360° content.
