www.uhasselt.be
DSpace

Document Server@UHasselt >
Research >
Research publications >

Please use this identifier to cite or link to this item: http://hdl.handle.net/1942/10271

Title: Stream-Centric Stereo Matching and View Synthesis: A High-Speed Approach on GPUs
Authors: Lu, Jiangbo
ROGMANS, Sammy
Lafruit, Gauthier
Catthoor, Francky
Issue Date: 2009
Publisher: IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Citation: IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 19(11). p. 1598-1611
Abstract: In this paper, we propose a real-time image-based rendering (IBR) system. It is specifically designed for photorealistic view synthesis at high-speed on the graphics processing unit (GPU). We steer the proposed IBR system design with two high-level ideas. First, for cost-effective IBR, as long as the synthesized views look visually plausible, the estimated disparity and occlusion need not be correct. Hence, we jointly optimize stereo matching and view synthesis for a favorable end-to-end performance. Second, for great real-time acceleration on GPUs, all functional modules need be shaped at an early design stage, fitting the massively parallel streaming architecture of GPUs. Based on these two guidelines, we first propose a stream-centric local stereo matching algorithm. The key idea is to construct a versatile set of variable support patterns in a highly efficient manner, and then an optimal local support pattern is selected to approximate varying image structures adaptively. Next, a low-complexity adaptive view synthesis technique is proposed. It efficiently tackles visual artifacts in synthesized images, using a novel photometric outlier detection and handling scheme. We evaluated both the disparity estimation accuracy and novel view synthesis quality of the proposed approach, based on the benchmark Middlebury stereo datasets. The experiments show that our local stereo method produces consistently reliable disparity estimates for both homogeneous regions and depth discontinuities, outperforming several previous GPU-based local methods. More importantly, visually plausible intermediate views are generated by our IBR approach at high-speed on the GPU. With stereo matching and view synthesis completely running on an NVIDIA GeForce 8800 GT graphics card, the proposed IBR system reaches about 100 f/s for 450x375 stereo images with 60 disparity levels.
Notes: [Lu, Jiangbo; Catthoor, Francky] Katholieke Univ Leuven, Dept Elect Engn, B-3001 Louvain, Belgium. [Lu, Jiangbo; Rogmans, Sammy] IMEC, Multimedia Grp, B-3001 Louvain, Belgium. [Lu, Jiangbo] Singapore Pte Ltd, ADSC Illinois, Singapore, Singapore. [Rogmans, Sammy] Hasselt Univ, Expertise Ctr Digital Media, B-3590 Diepenbeek, Belgium. [Lafruit, Gauthier] IMEC, Unit Smart Syst & Energy Technol, B-3001 Louvain, Belgium.
URI: http://hdl.handle.net/1942/10271
DOI: 10.1109/TCSVT.2009.2026948
ISI #: 000271600200004
ISSN: 1051-8215
Category: A1
Type: Journal Contribution
Validation: ecoom, 2010
Appears in Collections: Research publications

Files in This Item:

There are no files associated with this item.

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.