Figure - available from: Computer Graphics Forum
This content is subject to copyright. Terms and conditions apply.
We present a method that converts consumer‐grade omnidirectional stereo (ODS) recordings (left) to a multi‐sphere image (MSI) representation (middle). To this end we employ an encoder–decoder neural network structure as a tool for scene‐dependent optimization to estimate a temporally consistent MSI representation. While omnidirectional stereo (ODS) footage supports head rotation with realistic depth impression, it does not support head motion and free viewpoint rendering. In contrast the MSI representation enables immersive rendering with full head motion support for virtual reality applications (right).
Source publication
In this paper, we tackle the challenging problem of rendering real‐world 360° panorama videos that support full 6 degrees‐of‐freedom (DoF) head motion from a prerecorded omnidirectional stereo (ODS) video. In contrast to recent approaches that create novel views for individual panorama frames, we introduce a video‐specific temporally‐consistent mul...
Similar publications
This paper proposes an image dehazing prior, called Regional Saturation-Value Translation (RSVT), in order to address the color distortion issues produced by prevailing prior-based dehazing methods when processing hazy images with large sky regions. The proposed RSVT prior is derived from statistical analyses of the correlation between hazy points...
