DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Lee, Sung-Hee | - |
dc.contributor.advisor | 이성희 | - |
dc.contributor.author | Jung, Raehyuk | - |
dc.date.accessioned | 2021-05-13T19:38:50Z | - |
dc.date.available | 2021-05-13T19:38:50Z | - |
dc.date.issued | 2020 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=925192&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/285028 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 문화기술대학원, 2020.8,[iv, 28 p. :] | - |
dc.description.abstract | 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. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Computer vision▼adeep learning▼a360 imagery▼aimage orientation▼aupright adjustment | - |
dc.subject | 컴퓨터 비젼▼a딥 러닝▼a360 이미지▼a이미지 방향▼a직립 보정 | - |
dc.title | 360 image upright adjustment via deep learning | - |
dc.title.alternative | 딥러닝을 이용한 360 이미지의 직립보정 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :문화기술대학원, | - |
dc.contributor.alternativeauthor | 정래혁 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.