SVI360: Spherical Video Interpolation
arXiv:2607.11710
The paper introduces SVI360, a dual‑branch neural framework that improves interpolation of omnidirectional (360°) videos by combining the original view with a rotated orthogonal view and enforcing equivariant optical flow between them.
Abstract
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/
Accepted at ECCV 2026. Code and trained models are available at: https://icb-vision-ai.github.io/video360_interpolation/