منابع مشابه
Pano2Vid: Automatic Cinematography for Watching 360° Videos
We introduce the novel task of Pano2Vid — automatic cinematography in panoramic 360◦ videos. Given a 360◦ video, the goal is to direct an imaginary camera to virtually capture natural-looking normal field-of-view (NFOV) video. By selecting “where to look” within the panorama at each time step, Pano2Vid aims to free both the videographer and the end viewer from the task of determining what to wa...
متن کاملAutomatic Content-Aware Projection for 360° Videos
To watch 360 videos on normal 2D displays, we need to project the selected part of the 360 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 videos. Especially, we focus on the projection step preserving important image contents and reducing image distortion. Basically, our projection me...
متن کاملSupplementary Material: Deep 360 Pilot: Learning a Deep Agent for Piloting through 360◦ Sports Videos
r(lt(i), l gt t ) = { 1− ‖lt(i)−l gt t ‖2 η , if ‖lt(i)− l gt t ‖2 <= η −1, otherwise (1) where η equals the distance from the center of a viewing angle to the corner of its corresponding NFoV, i.e., √ 32.752 + 24.562 = 40.9 if we define NFOV as spanning a horizontal angle of 65.5◦ with a 4 : 3 aspect ratio. When lt == l gt t , the reward is 1, which is the maximum reward. When ‖lt(i) − l t ‖2 ...
متن کاملVisual Attributes in Videos
Attributes are descriptive characteristics with crosscategory applicability. They can be used to provide additional information that is not found in simple object classification, giving the computer a complete picture of the item and the state in which it appears. While attribute prediction has been studied extensively in still images, this is not the case in videos. However, there exist visual...
متن کاملDeep 360 Pilot: Learning a Deep Agent for Piloting through 360° Sports Videos
Watching a 360 sports video requires a viewer to continuously select a viewing angle, either through a sequence of mouse clicks or head movements. To relieve the viewer from this “360 piloting” task, we propose “deep 360 pilot” – a deep learning-based agent for piloting through 360 sports videos automatically. At each frame, the agent observes a panoramic image and has the knowledge of previous...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Transactions on Circuits and Systems for Video Technology
سال: 2020
ISSN: 1051-8215,1558-2205
DOI: 10.1109/tcsvt.2019.2927344