A NOVEL PLANAR LAYERED REPRESENTATION FOR 3DTV AND FREEVIEW TV APPLICATIONS

Date

2013-07-19

Author

Ozkalayci, Burak
Alatan, Abdullah Aydın

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

31
views

0
downloads

A novel planar layered representation for 3D content is proposed. The proposed representation aims to decouple the geometric and textural distortion related artifacts in novel view rendering. In this perspective, an energy minimization-based framework is utilized to fit planar models from 3D range data. The planar model assignments provide object-like segmentation of the scene. By rendering the corresponding texture information of the planar assignments, the proposed representation is finalized. In novel view rendering applications, the proposed representation shows minimum artifacts with different characteristics with respect to the conventional approaches. The experimental results of the proposed representation are quite promising for various datasets.

Subject Keywords

Model fitting, Multiview plus depth, Graph cut, Depth image based rendering

URI

https://hdl.handle.net/11511/55088

Conference Name

IEEE International Conference on Multimedia and Expo Workshops (ICMEW)

Collections

Department of Electrical and Electronics Engineering, Conference / Seminar

Suggestions

OpenMETU
Core

Extraction of 3D transform and scale invariant patches from range scans Akagunduz, Erdern; Ulusoy, İlkay (2007-06-22) An algorithm is proposed to extract transformation and scale invariant 3D fundamental elements from the surface structure of 3D range scan data. The surface is described by mean and Gaussian curvature values at every data point at various scales and a scale-space search is performed in order to extract the fundamental structures and to estimate the location and the scale of each fundamental structure. The extracted fundamental structures can later be used as nodes in a topological graph where the links betw...
3D object recognition using scale space of curvatures Akagündüz, Erdem; Ulusoy, İlkay; Department of Electrical and Electronics Engineering (2011) In this thesis, a generic, scale and resolution invariant method to extract 3D features from 3D surfaces, is proposed. Features are extracted with their scale (metric size and resolution) from range images using scale-space of 3D surface curvatures. Different from previous scale-space approaches; connected components within the classified curvature scale-space are extracted as features. Furthermore, scales of features are extracted invariant of the metric size or the sampling of the range images. Geometric ...
Compressed Representation of High Dimensional Channels using Deep Generative Networks Doshi, Akash; Balevi, Eren; Andrews, Jeffrey G. (2020-05-01) © 2020 IEEE.This paper proposes a novel compressed representation for high dimensional channel matrices obtained by optimization of the input to a deep generative network. Channel estimation using generative networks constrains the reconstructed channel to lie in the range of the generative model, which allows it to outperform conventional channel estimation techniques in the presence of limited number of pilots. It also eliminates the need for explicit knowledge of the sparsifying basis for mmWave multiple...
A New Method for Generating Image Projections in DLP-type 3D Printer Systems Yaman, Ulaş; Dölen, Melik (Elsevier BV, 2017-01-01) This paper presents a novel method for generating image projections required for Digital Light Processing type 3D printer systems where the entire cross-section of the printed object is directly formed via projecting the image onto a vat of photopolymers. The cross-sections (i.e. slices), which are initially represented as bitmap images, are compressed via a novel lossless compression technique which makes good use of relative data encoding. The coherence between the consecutive slices (or images) are taken...
TEMPORALLY CONSISTENT LAYER DEPTH ORDERING VIA PIXEL VOTING FOR PSEUDO 3D REPRESENTATION Turetken, Engin; Alatan, Abdullah Aydın (2009-05-06) A new region-based depth ordering algorithm is proposed based on the segmented motion layers with affine motion models. Starting from an initial set of layers that are independently extracted for each frame of an input sequence, relative depth order of every layer is determined following a bottom-to-top approach from local pair-wise relations to a global ordering. Layer sets of consecutive time instants are warped in two opposite directions in time to capture pair-wise occlusion relations of neighboring lay...

Citation Formats

B. Ozkalayci and A. A. Alatan, “A NOVEL PLANAR LAYERED REPRESENTATION FOR 3DTV AND FREEVIEW TV APPLICATIONS,” presented at the IEEE International Conference on Multimedia and Expo Workshops (ICMEW), San Jose, CA, 2013, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/55088.