# Automatic Content-aware Projection for 360{\deg} Videos

## TL;DR

This paper introduces an automated, content-aware projection framework for converting 360-degree videos into normal-view videos, focusing on preserving important content and reducing distortion with high efficiency.

## Contribution

It presents a novel, fully-automated projection method based on Panini models that preserves salient content, minimizes distortion, and ensures temporal stability without user interaction.

## Key findings

- Outperforms previous methods in preserving content and reducing distortion
- Achieves faster processing times compared to existing content-preserving techniques
- Produces more stable and visually appealing normal-view videos from 360{ extdegree} content

## Abstract

To watch 360{\deg} videos on normal 2D displays, we need to project the selected part of the 360{\deg} image onto the 2D display plane. In this paper, we propose a fully-automated framework for generating content-aware 2D normal-view perspective videos from 360{\deg} videos. Especially, we focus on the projection step preserving important image contents and reducing image distortion. Basically, our projection method is based on Pannini projection model. At first, the salient contents such as linear structures and salient regions in the image are preserved by optimizing the single Panini projection model. Then, the multiple Panini projection models at salient regions are interpolated to suppress image distortion globally. Finally, the temporal consistency for image projection is enforced for producing temporally stable normal-view videos. Our proposed projection method does not require any user-interaction and is much faster than previous content-preserving methods. It can be applied to not only images but also videos taking the temporal consistency of projection into account. Experiments on various 360{\deg} videos show the superiority of the proposed projection method quantitatively and qualitatively.