2026-09-21T04:55:38Z https://www.ideals.illinois.edu/oai-pmh

oai:www.ideals.illinois.edu:2142/18553 2023-07-10 col_2142_5131 col_2142_8888 com_2142_5130 com_2142_8887 com_2142_234

Ahuja, Narendra Ahuja, Narendra Boppart, Stephen A. Forsyth, David A. Hoiem, Derek W. Huang, Thomas S. Yang, Qingxiong 2011-01-21T22:45:47Z 2011-01-21T22:45:47Z 2013-01-22T11:00:25Z 2011-01-21T22:45:47Z 2010-12 In this dissertation, I report the progress towards building a robust and efficient 3D reconstruction system based on stereo vision. Stereo vision is known to be quite fragile in practice due to specular highlights, lack of texture, lighting variations, image blurring, etc. In this dissertation, I focus on exploiting the relationships between illuminants, surface reflection and shape to increase the robustness of stereo vision. I first present a new image transform for matching low-textured regions and then a robust solution for illumination chromaticity estimation based on a new correspondence matching invariant called Illumination Chromaticity Constancy. I next propose a new framework based on bilateral filtering and loopy belief propagation for simultaneous estimation of surface reflectance and shape with the assumption that the illumination chromaticity can be correctly estimated. Two new bilateral filtering algorithms with computational complexity invariant to filter kernel size and a new belief propagation with computational complexity invariant to the disparity search range are then presented to reduce the speed and memory cost. Item withdrawn by Mark Zulauf (zulauf@illinois.edu) on 2010-11-30T14:54:16Z Item was in collections: University of Illinois Theses & Dissertations (ID: 1) No. of bitstreams: 1 Yang_Qingxiong.pdf: 17344259 bytes, checksum: e4223bc954148514a6f424a0fb570cee (MD5) Made available in DSpace on 2011-01-21T22:45:47Z (GMT). No. of bitstreams: 2 Yang_Qingxiong.pdf: 17344259 bytes, checksum: e4223bc954148514a6f424a0fb570cee (MD5) license.txt: 4062 bytes, checksum: 315a02abd9a1324515fe2751f9df6fd0 (MD5) Item marked as restricted to the 'UIUC Users [automated]' Group (id=2) by William Ingram (wingram2@illinois.edu) on 2011-01-21T22:48:14Z Item is restricted until 2013-01-21T22:47:37Z Item reinstated by Sarah Shreeves (sshreeve@illinois.edu) on 2013-01-22T11:00:25Z Item was in collections: University of Illinois Dissertations and Theses (ID: 204) Dissertations and Theses - Electrical and Computer Engineering (ID: 446) No. of bitstreams: 3 Yang_Qingxiong.pdf.txt: 189551 bytes, checksum: dc01ab5eaf357cfd5b7d2ff8b5ed8e04 (MD5) Yang_Qingxiong.pdf: 17344259 bytes, checksum: e4223bc954148514a6f424a0fb570cee (MD5) license.txt: 4062 bytes, checksum: 315a02abd9a1324515fe2751f9df6fd0 (MD5) Item released from any restrictions by Sarah Shreeves (sshreeve@illinois.edu) on 2013-01-22T11:00:25Z http://hdl.handle.net/2142/18553 en Copyright 2010 Qingxiong Yang Stereo Matching Bilateral Filter Belief Propagation Robust and efficient image-based 3D modeling Electrical & Computer Eng 1933 Electrical & Computer Engr 1200 University of Illinois at Urbana-Champaign Dissertation Ph.D. PHD:Electr & Computer Eng-UIUC 10KS1200PHD