Planar 3d scene representations for depth compression

Download
2014
Özkalaycı, Burak Oğuz
The recent invasion of stereoscopic 3D television technologies is expected to be followed by autostereoscopic and holographic technologies. Glasses-free multiple stereoscopic pair displaying capabilities of these technologies will advance the 3D experience. The prospective 3D format to create the multiple views for such displays is Multiview Video plus Depth (MVD) format based on the Depth Image Based Rendering (DIBR) techniques. The depth modality of the MVD format is an active research area whose main objective is to develop DIBR friendly efficient compression methods. As a part this research, the thesis proposes novel 3D planar-based depth representations. The planar approximation of the stereo depth images is formulated as an energy-based co-segmentation problem by a Markov Random Field model. The energy terms of this problem are designed to mimic the rate-distortion tradeoff for a depth compression application. A heuristic algorithm is developed for practical utilization of the proposed planar approximations in stereo depth compression. The co-segmented regions are also represented as layered planar structures forming a novel single referenced MVD format. The proposed planar based depth compression solutions are compared against the state-of-the art image/video and MVD compression standards. The compression performances are analyzed for depth reconstruction and novel view rendering by DIBR techniques. All the experiments are performed with the ground truth texture of the MVD data, since the scope of the thesis is limited with the depth modality. The visual and objective evaluations show that the proposed planar representations are promising for efficient depth compression with artifact-free novel view rendering. As a remarkable contribution, the proposed layered planar MVD representation also brings the depth perception quality considerations in the MVD compression schemes by decoupling the texture and geometry to a wide extent.
Citation Formats
B. O. Özkalaycı, “Planar 3d scene representations for depth compression,” Ph.D. - Doctoral Program, Middle East Technical University, 2014.