Planar 3d scene representations for depth compression

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.


Range data recognition: segmentation, matching, and similarity retrieval
Yalçın Bayramoğlu, Neslihan; Alatan, Abdullah Aydın; Department of Electrical and Electronics Engineering (2011)
The improvements in 3D scanning technologies have led the necessity for managing range image databases. Hence, the requirement of describing and indexing this type of data arises. Up to now, rather much work is achieved on capturing, transmission and visualization; however, there is still a gap in the 3D semantic analysis between the requirements of the applications and the obtained results. In this thesis we studied 3D semantic analysis of range data. Under this broad title we address segmentation of range...
3D object recognition from range images
İzciler, Fatih; Halıcı, Uğur; Department of Electrical and Electronics Engineering (2012)
Recognizing generic objects by single or multi view range images is a contemporary popular problem in 3D object recognition area with developing technology of scanning devices such as laser range scanners. This problem is vital to current and future vision systems performing shape based matching and classification of the objects in an arbitrary scene. Despite improvements on scanners, there are still imperfections on range scans such as holes or unconnected parts on images. This studyobjects at proposing an...
Photometric stereo considering highlights and shadows
Büyükatalay, Soner; Halıcı, Uğur; Birgül, Özlem; Department of Electrical and Electronics Engineering (2011)
Three dimensional (3D) shape reconstruction that aims to reconstruct 3D surface of objects using acquired images, is one of the main problems in computer vision. There are many applications of 3D shape reconstruction, from satellite imaging to material sciences, considering a continent on earth or microscopic surface properties of a material. One of these applications is the automated firearm identification that is an old, yet an unsolved problem in forensic science. Firearm evidence matching algorithms rel...
Real - time stereo to multi-view video conversion
Çığla, Cevahir; Alatan, Abdullah Aydın; Department of Electrical and Electronics Engineering (2012)
A novel and efficient methodology is presented for the conversion of stereo to multi-view video in order to address the 3D content requirements for the next generation 3D-TVs and auto-stereoscopic multi-view displays. There are two main algorithmic blocks in such a conversion system; stereo matching and virtual view rendering that enable extraction of 3D information from stereo video and synthesis of inexistent virtual views, respectively. In the intermediate steps of these functional blocks, a novel edge-p...
3D Face Reconstruction Using Stereo Images and Structured Light
OZTURK, Ahmet Oguz; Halıcı, Uğur; ULUSOY PARNAS, İLKAY; AKAGUNDUZ, Erdem (2008-04-22)
In this paper, the 3D face scanner that we developed using stereo cameras and structured light together is presented. Structured light having a pattern of vertical lines is used to create feature points and to match them easily. 3D point cloud obtained by stereo analysis is post processed to obtain the 3D model in obj format.
Citation Formats
B. O. Özkalaycı, “Planar 3d scene representations for depth compression,” Ph.D. - Doctoral Program, Middle East Technical University, 2014.