Spherical VR cameras can capture high-quality immersive VR images with a 360◦ field of view. However, in practice, when the camera orientation is not straight, the acquired VR image appears tilted
when displayed on a VR headset, which diminishes the quality of the VR experience. To overcome this
problem, we present a deep learning-based approach that can automatically estimate the orientation of a
VR image and return its upright version. In contrast to existing methods, our approach does not require
the presence of lines or horizon in the image, and thus can be applied on a wide range of scenes. rae>
We first suggest a simple neural network architecture. This is composed of a CNN layer and a fully connected layers. After that we further investigate a better architecture that preserves spatial relationship
of pixels in the 360 image. The graph convolutional layer is exploited to achieve the preservation. The
latter version of network architecture demonstrates gain of accuracy without additional parameters nor
gain of computation cost. Extensive experiments and comparisons with state-of-the-art methods have
successfully confirmed the validity of our approach.
Spherical VR 카메라는 360도의 horizontal FoV, 180도의 vertical FoV를 갖는 카메라이다. 일반적인 상황에
서 특수한 장비 없이 Spherical VR 카메라를 이용하여 사진을 촬영하면 사진의 방향이 직립하지 못한 경우가
대다수 이다. 해당 논문에서는 360도 이미지의 직립보정을 위하여 딥러닝 기반의 알고리즘을 제시한다. 첫
번째로, 가장 단조로운 네트워크 구조로 시작하여 해당 연구의 타당성을 입증한후 Graph neural network
를 차용하여 조금 더 개량된 형태를 소개한다. 양적인, 질적인 평가를 통하여 해당 알고리즘의 타당성을
검증한다.