解决全景视频插帧中的极区畸变问题，提升沉浸式视频质量。
SVI360: Spherical Video Interpolation
- 采用双分支结构融合原图与正交旋转视图，增强流场等变性。
- 在4个公开数据集上均优于现有方法，插值质量更优。
- 适合虚拟现实、全景视频增强等需要高精度插帧的场景。
本文针对全景视频插帧问题展开研究，该问题在虚拟现实和沉浸式视频增强中具有关键作用。现有插帧方法难以处理极区附近的严重畸变。为此，我们提出SVI360，一种双分支框架，通过结合图像帧与其旋转后的正交视图来缓解畸变问题。核心思路是强化原图与正交视图间光流位移的等变性，从而提升中间帧预测精度。实验表明，该方法在4个不同公开基准上均优于当前最优方法，在插帧质量和光流准确性方面表现优异。代码与预训练模型已开源：https://icb-vision-ai.github.io/video360_interpolation/
原文摘要 · Abstract (English)
This paper addresses the problem of omnidirectional video interpolation, which plays an essential role in applications such as virtual reality and immersive video enhancement. Existing video interpolation methods are not well-suited for spherical videos, as they have difficulty handling severe distortions close to the poles. To address this issue, we propose SVI360, a dual-branch framework that combines the image frame and its rotated orthogonal view to deal with these distortions. The core methodological aspect of the approach is to reinforce equivariance of the flow displacements between the original and orthogonal views to improve intermediate frame prediction. Experiments show that our method outperforms state-of-the-art approaches in interpolation quality while maintaining accurate optical flow in four different public benchmarks. Code and pre-trained models are available at: https://icb-vision-ai.github.io/video360_interpolation/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。